27 results about "Surface projection" patented technology

The invention discloses a tunnel lining crack identification method and system based on panoramic space image splicing, and relates to the technical field of tunnel visual identification. The method comprises the following steps: acquiring a tunnel lining image array, and performing local splicing on tunnel lining images by using a splicing model based on cylindrical surface projection to obtain a local spliced image; fusing and splicing the local spliced images by using the global image space model to obtain a panoramic spliced data graph; and abnormal region detection is carried out on the panoramic splicing data graph according to the spatial local difference, and a tunnel lining crack identification result is obtained. According to the method, the lining panoramic space model based on image two-stage fusion is used for splicing, so that the visual coherence and naturalness of a global spliced image are improved.

The invention relates to the technical field of ultrasonic detection, and discloses an ultrasonic scanning path optimization and three-dimensional reconstruction method, device, equipment and medium, and the method comprises the steps: positioning a key mark point of a target area, generating an initial scanning path, and controlling an ultrasonic probe to move along the initial scanning path to collect first ultrasonic image data, extracting target structure features to construct an initial three-dimensional point cloud model; establishing a surface projection model; fitting to generate a surface profile curve and calculating the tangential direction of a sampling point; optimizing the orientation of an ultrasonic probe based on the tangential direction to generate an optimized scanning path; and reconstructing a final three-dimensional model. According to the invention, through key mark point positioning and incident direction optimization based on the tangential direction, the scanning path of the probe is enabled to be adaptive to curvature change of the target area, and through combination of real-time contact force adjustment and multi-stage image data acquisition, three-dimensional point cloud space coverage and imaging consistency are improved, and high-precision three-dimensional reconstruction of a complex anatomical structure is realized.

The invention relates to the technical field of computer aided design, in particular to a neighborhood gradient-oriented large-curvature curved surface projection point calculation method, which comprises the following steps of: S1, calculating a space bounding box of a curved surface to be projected, and performing triangulation to generate a triangular mesh; s2, traversing curved surface control vertexes of the triangular mesh, recording an adjacent vertex set, and judging whether the vertex set is a boundary point or not according to the UV parameter coordinates; s3, storing the vertex information and constructing a BVH tree, traversing the BVH tree for a to-be-projected point, querying and obtaining the nearest vertex with the minimum distance from the to-be-projected point, judging whether the nearest vertex is a boundary point or not, and processing according to a judgment result to obtain an iteration initial value; and S4, constructing a target function by taking the iteration initial value as an initial value, and calculating by using a Newton iteration method to obtain an accurate projection point of the to-be-projected point on the curved surface. The curved surface projection point approximation result calculation method is high in calculation efficiency and robustness, and the influence of curvature, grid division and other factors on Newton iteration input is reduced.

This invention provides an automatic calibration method and apparatus for a ship panoramic surround view system based on UAV collaboration and 3D surface mapping. A virtual 3D surface projection model is established in the ship's coordinate system, and the surface normal vectors of sampling points on this model are mapped outwards to generate the UAV's flight trajectory. The UAV, equipped with an RTK positioning module, acts as a dynamic calibration target with precise three-dimensional coordinates as it flies along this trajectory, its spatial distribution naturally matching the geometry of the surface projection model. During flight, images from the UAV are simultaneously acquired by the ship's onboard camera, and pixel coordinates are extracted using a target detection algorithm. Simultaneously, the time synchronization data between the UAV and the ship's onboard RTK module is used to establish the correspondence between pixel coordinates and three-dimensional coordinates in the ship's coordinate system, minimizing reprojection errors and jointly calculating the extrinsic parameters of each camera. This eliminates the dependence on fixed planar references on shore, enabling automated calibration with precise adaptation to the 3D surface projection model in any water area.

The application discloses a saw blade detection system based on multi-source data fusion, and particularly relates to the technical field of saw blade detection; the saw blade detection system is characterized in that: side surface image data of a saw blade is collected, tooth back surface projection line features and edge geometry features are extracted, initial visual feature data of the saw blade is established; side surface image data is continuously collected in actual processing, side edge projection line features and edge position changes are compared and analyzed, visual wear data is determined; main shaft current data is synchronously collected and current change trends and variability are analyzed, current wear data is determined; normal wear and tooth loss abnormal trends of the saw blade are analyzed based on the visual wear data and the current wear data, visual degradation features and current abnormal features are obtained; visual and current fusion feature data is calculated in combination with product processing unqualified rate, and a saw blade scrapping trigger threshold is established; finally, fusion feature data and the scrapping threshold are compared in real time, so that the saw blade scrapping or replacement time is determined; and the application improves the precision and reliability of saw blade state monitoring.

The application discloses an initialization method of a conic surface under a projection linearization track surface, and belongs to the technical field of calculation, reckoning or counting. The method first obtains a preliminary estimation of a target track through three groups of observation data; determines a conic surface containing an initial track surface according to initial track information and geometric knowledge; estimates the missing height information in combination with the conic surface, and obtains more position information of the target in combination with the existing angle information; projects the position information of the target into a two-dimensional section, re-estimates the track parameters by using a least square algorithm, and more accurate track parameters can be obtained; then the iteration process is repeated by using the newly obtained track information until a certain initial orbit determination accuracy requirement is met. The algorithm firstly fits the height information of the target by using a conic surface coordinate system, and realizes linear fitting of the position vector by using a track surface projection method, so that the calculation amount is small and the accuracy is high.

The invention discloses a directed distance field particle shape representation processing method, system and platform based on a neural network. According to the core technology principle of the particle mechanical modeling and simulation method based on the neural network coding directed distance field, three-dimensional space coordinates are mapped into directed distance values (SDF) through multi-layer sensor (MLP) neural network learning, and therefore particles in any complex shape are implicitly represented; multi-shape unified modeling and virtual particle generation are realized by introducing a potential coding mechanism, and efficient surface projection and contact detection are realized by adopting a gradient descent and ray search combined method; finally, the trained NetSDF model and a discrete element method (DEM) are seamlessly integrated, and efficient simulation of the large-scale particle system is achieved through acceleration. The method breaks through the limitation of the traditional shape representation method in the aspects of precision, memory and computational efficiency, and provides a brand new solution for computational modeling of the granular material.

The application provides a double-curvature fusion curved surface SLAM navigation method, a longitudinal and transverse double-direction curvature parameter is estimated in real time through double-IMU fusion, an extended information filtering framework containing a double-curvature kinematic model, a laser data curved surface projection compensation algorithm and a path double-curvature compensation algorithm are constructed, and the scheme can accurately depict the curved surface geometric constraint where the robot actually locates; the accumulation of the transverse positioning error is inhibited through online estimation and fusion of the transverse curvature parameter; the accurate description and compensation of the robot side slip effect are realized through the establishment of a kinematic model containing a double-curvature coupling term; the data distortion is eliminated and the environment perception accuracy is improved through the projection of the laser scanning data from a plane to the estimated curved surface; finally, the consistency of the control instruction and the curved surface geometry is ensured through the real-time geometric compensation of the planning path based on the double-curvature parameter, and the stability and trajectory tracking accuracy of the control system under the longitudinal and transverse curvature coupling effect are enhanced.

The invention relates to a surface disinfection system. The surface disinfection system comprises: - a laser beam scanner as a projection device (22, 22'', 22''') with a beam generator (140) for generating a light beam (LBM) and a mirror unit (73) for reflecting the light beam (LBM) and for moving the reflected light beam (LBR) over a predetermined solid angle range; wherein the projection device (22, 22'', 22''') has a light source with a wavelength of less than 475 nm, - a projection surface (21, 21'', 21''') over which the light beam (LBR) emitted by the projection device (22, 22'', 22''') can be moved, and - a computing unit (52) which is designed to control the intensity and illumination time of the light beam emitted by the projection device (22, 22'', 22''').

The utility model discloses a device with a multi-surface projection function, and belongs to the technical field of multi-surface projection. A support is fixedly installed at the top of a display wall, a sliding groove is formed in the bottom of the support, a sliding block is installed in the sliding groove in a matched mode, and a projector hanging bracket is fixedly connected to the bottom of the sliding block; a first projector is arranged on one side of the support, and a projector hanging bracket is arranged on the other side of the support. The projector hanging bracket is arranged in a hollow mode, a second projector and a third projector are fixedly connected to the two sides of the bottom of the projector hanging bracket, and a fourth projector is arranged in the hollow portion of the projector hanging bracket and fixedly connected with the projector hanging bracket; according to the utility model, the projector hanging bracket can be flexibly moved, the position and angle of the projector can be conveniently adjusted so as to adapt to different display spaces and projection requirements, the projection flexibility is further improved, and the position and direction of a projection picture can be accurately adjusted according to actual conditions.

The present application relates to the technical field of geotechnical engineering, in particular to a rock joint roughness measurement method and system. The present application first acquires a triangular mesh of the rock surface; further based on the spatial distribution of the unit outer normal vector in the global coordinate system, and shielding detection is carried out on the local surface element along the shear reverse direction, and the potential contact surface element is screened out; further analyzing each potential contact surface element in the global coordinate system, combining the preset working condition parameters to calculate the friction sliding work; further acquiring the rock mass support thickness, and combining the preset working condition parameters and the shear surface projection area to calculate the root truncation work; further comparing the root truncation work and the friction sliding work, marking the energy consumption mode and constructing the shear energy consumption directed graph, calculating the equivalent shear roughness, solving the problem that the traditional method mistakenly counts the thin ridge protrusions prone to shearing into the roughness under high stress, realizing the stress-sensitive effective roughness measurement.

The application discloses an emergency trauma wound area intelligent measurement and recording system based on deep learning, relates to the field of computer vision, synchronously acquires a two-dimensional image sequence, a six-axis attitude vector and a time stamp, extracts a mask by using a segmentation network, and constructs a local curved surface geometric model in combination with prior parameters; a non-homogeneous weight compensation matrix is generated by calculating the included angle distribution of a space vector and an optical axis vector; target wound physical surface areas are acquired by performing pixel-by-pixel weighted integration on mask pixels based on the matrix, and the shrinkage caused by projection is compensated. According to the weight matrix gradient, confidence is evaluated, and dynamic acquisition guidance or structured data encapsulation is realized. The application effectively corrects non-homogeneous curved surface projection distortion, and improves measurement accuracy and the reliability of clinical records.

The invention relates to the technical field of projection, in particular to a short-focus projection design method and device suitable for a curved surface target and a storage medium. According to the method, a basic system is constructed through optical design, key coordinates are obtained through field point translation and ray tracing in combination with characteristics of a curved surface target, a mapping relation is accurately established by means of a radial basis function, and a pre-distortion image is generated. The method is advantaged in that adaptation to a curved surface target is realized, problems of distortion, non-uniform brightness and the like which are easy to occur in curved surface projection are effectively solved, clear images, no obvious deformation and no extra complex optical elements after projection are guaranteed, rapid deployment can be realized, and short-focus projection can stably output high-quality images on the curved surface.

The present application relates to the technical field of centrifugal pump, in particular to a centrifugal pump blade wrap angle determination method based on fluid mechanics numerical integration. The centrifugal pump blade wrap angle determination method is a numerical integration method based on fluid mechanics equation. By combining differential equation and numerical integration, equidistant points are divided on the axial surface streamline in the axial surface projection diagram, and the arc length and radius between each adjacent two equidistant points are calculated. Based on one-dimensional flow theory, the axial surface fluid velocity v m is calculated m , and a curve changing along the axial surface streamline is drawn. According to Euler equation, a linear distribution model of tangential velocity moment v u r is established. After calculating the integral coefficient K, K·△s i is calculated point by point, and the integral is accumulated to directly obtain the centrifugal pump blade wrap angle value. The effectiveness of the centrifugal pump blade wrap angle value is verified by using an example verification method. The present application can realize the design of the centrifugal pump blade wrap angle through parameterization, and get rid of the condition that the centrifugal pump blade wrap angle can only be obtained by relying on experience.

This invention provides a self-supervised arbitrary-scale point cloud upsampling method and system, including: automatically adjusting the point density of midpoint interpolation using a local geometric feature analysis module to construct an intermediate candidate point set; obtaining interpolation points by controlling the arbitrary-scale upsampling ratio of the intermediate candidate point set through farthest-point sampling technology; introducing an implicit surface projection optimization mechanism, using the interpolation points as seed points for two-stage optimization, and achieving surface projection by estimating the projection direction and projection distance through an implicit neural function; and optimizing the boundary feature representation of the surface projection by generating a two-dimensional projection map through dynamic scaling of the sparse input point cloud based on a pseudo-true value projection comparison mechanism based on point cloud scale transformation. Through adaptive dynamic neighborhood optimization of local geometric features, arbitrary-scale upsampling ratio control, combined with estimation of projection direction and projection distance, and pseudo-true value projection comparison mechanism, the method ensures geometric detail fidelity, point cloud uniformity, and arbitrary-scale generalization ability.

The application discloses a fan regular inspection control method and system of PLC and robot cooperation, which sets an initial threshold value by using an edge computing gateway in combination with PLC macro environment data, collects sensor data and attitude information in real time during robot operation, and executes online quality evaluation. For visual data, a weighted evaluation mechanism based on three-dimensional geometric projection fidelity is particularly introduced, distortion Jacobian graph is used to correct the evaluation deviation caused by surface projection, and the quality score is ensured to truly reflect the observation condition of the physical surface. Based on the quality state mark obtained in real time, action intention is automatically decided and generated, and the motion speed of the robot, the sensor parameter or the micro-correction path is dynamically adjusted. This mechanism enables the inspection system to adaptively respond to environmental changes such as light and surface stains, effectively improving the robustness and data effectiveness of fan automatic inspection.

The invention provides a self-supervised arbitrary scale point cloud up-sampling method and system, and the method comprises the steps: employing a local geometric feature analysis module to automatically adjust the point density of midpoint interpolation, and constructing an intermediate candidate point set; carrying out sampling proportion control on the middle candidate point set at any scale through a farthest point sampling technology to obtain interpolation points; an implicit curved surface projection optimization mechanism is introduced, an interpolation point is used as a seed point to carry out dual-stage optimization, and a projection direction and a projection distance are estimated through an implicit neural function to realize curved surface projection; based on a pseudo-true value projection comparison mechanism of point cloud scale transformation, a two-dimensional projection drawing is generated by dynamically scaling sparse input point cloud, and boundary feature expression of curved surface projection is optimized. Through local geometric feature adaptive dynamic neighborhood optimization and arbitrary scale up-sampling proportion control, in combination with projection direction and projection distance estimation and a pseudo-true value projection comparison mechanism, geometric detail fidelity, point cloud uniformity and arbitrary scale generalization ability are ensured.

This invention discloses a machine vision-based real-time detection method for the surface hardness distribution of pins, belonging to the field of image extraction technology. The machine vision-based real-time detection method for the surface hardness distribution of pins includes: S1, acquiring and preprocessing the surface hardness distribution detection data of the pins, storing and constructing a pin hardness database; S2, performing surface unfolding correction analysis based on circumferential rotation angle values, local curvature values, surface tilt values, and edge grayscale transition width values; S3, constructing an indentation geometric recovery model by introducing the surface unfolding correction value and the original geometric parameters of the indentation; S4, conducting an indentation stability assessment based on the indentation geometric recovery parameters, center reflection offset value, and indentation geometric reliability value, and outputting the surface hardness value; S5, analyzing hardness fluctuations by combining the surface hardness value, indentation stability value, surface unfolding correction value, and circumferential rotation angle value. This method solves the problems of indentation size measurement errors and hardness result fluctuations caused by surface projection distortion during surface hardness detection.

The invention discloses a polyester filament yarn spinning on-line detection system and method based on machine vision, and belongs to the technical field of chemical fiber production quality control. The system drives the detection terminal to follow up in real time through the spatial position locking unit, and the physical working distance between the light field shielding unit and the surface of the spinning cake and the physical working distance between the internal optical assembly and the surface of the spinning cake are locked to be constant values; in the stable geometric boundary, narrow-band light and a constant incidence angle are utilized to construct an anisotropic scattering field, internal transmission light is physically cut off, and surface projection is enhanced; and finally, the data processing center calculates the physical height of the defect from the scattered field image through a calculation model containing light loss compensation and jitter suppression items. According to the invention, stable quantitative detection of the spinning cake surface microstructure under the dynamic winding working condition is realized.

The application belongs to the technical field of underground engineering, and discloses a tunnel fissure rock mass grouting diffusion radius and hole arrangement design method and system, which comprises the following steps: a three-dimensional model of tunnel fissure is established within the grouting range, a fissure fitting surface is obtained according to the model, a center of the fissure fitting surface is obtained, the center is projected on the tunnel face to obtain a fissure surface projection point; all the fissure surface projection points are clustered and grouped, and a minimum covering circle of each cluster group is established to obtain the center coordinates and the radius of the minimum covering circle; the relationship between the slurry diffusion radius and the grouting hole position and quantity is established in each minimum covering circle; and the slurry diffusion radius and the grouting hole quantity are iteratively optimized to obtain the optimal slurry diffusion radius and the grouting hole quantity. The application effectively reduces the subjectivity in the traditional design method, improves the scientificity and accuracy of the grouting scheme, and thus improves the effect and economic benefit of grouting reinforcement.

According to the double-curvature fusion curved surface SLAM navigation method provided by the invention, longitudinal and transverse two-way curvature parameters are estimated in real time through double IMU fusion, and a scheme including an extended information filtering framework of a double-curvature kinematics model, a laser data curved surface projection compensation algorithm and a path double-curvature compensation algorithm is constructed; the geometric constraint of the actual curved surface of the robot can be accurately described; accumulation of transverse positioning errors is inhibited through online estimation and fusion of transverse curvature parameters; by establishing a kinematics model containing a double-curvature coupling item, accurate description and compensation of the robot sideslip effect are realized; by projecting laser scanning data from a plane to an estimated curved surface, data distortion is eliminated, and environmental perception precision is improved; finally, real-time geometric compensation is carried out on the planned path based on double curvature parameters, the consistency of a control instruction and curved surface geometry is ensured, and the stability and trajectory tracking precision of a control system under the longitudinal and transverse curvature coupling effect are enhanced.

The invention discloses a light source pose calibration system, a light source pose calibration method, a controller and a medium. The system comprises a light source to be adjusted; the projection plate is arranged below the light source to be adjusted, the projection plate comprises a transparent plate, an upper surface shielding layer and a lower surface projection imaging layer, the upper surface shielding layer is arranged on the upper surface of the transparent plate, the lower surface projection imaging layer is arranged on the lower surface of the transparent plate, and a plurality of photometric patterns are arranged on the upper surface shielding layer; under the condition that the to-be-adjusted light source is turned on, the photometric pattern forms a projection image on the lower surface projection imaging layer; and the image acquisition equipment is arranged above the to-be-adjusted light source and is used for acquiring an image of the projection plate under the condition that the to-be-adjusted light source is turned on. The projection plate adopts the double-layer structure, the photometric pattern of the upper surface shielding layer forms clear projection on the lower projection imaging layer, the projection image can be accurately captured, and the accuracy and efficiency of light source pose calibration are improved through the projection corresponding relation of the double-layer structure.

The invention relates to the technical field of optical lens design, and discloses a Fermat spiral golden angle offset lens arrangement method and system.The method comprises the steps that lens parameters are obtained, a curved surface polar coordinate system is established, a Fermat spiral model is adopted to generate an initial dot matrix, uniformity is evaluated through Voronoi space subdivision, and a final lens array is obtained. Self-adaptive offset optimization is carried out in a golden angle critical range, a central vision protection area is applied to constrain and restore the uniformity of an inner ring, a pre-distortion compensation mechanism is adopted when curved surface projection mapping is executed, optical parameters of the microstructure are configured according to the radial position, and finally a digital processing file is generated. According to the invention, high-uniformity isotropic arrangement of the microstructures can be realized on the curved surface of the lens, and the technical problems that the existing periodic arrangement generates structured artifacts and the existing non-periodic arrangement lacks adaptive optimization capability are solved.

The invention discloses a square cabin panoramic display method adaptive to a virtual driving scene, which comprises a square cabin body which is of a tetrahedral structure, four inner side surfaces of the square cabin body serve as projection bearing surfaces, and comprises the following steps: S1, initializing a virtual driving simulation module; s2, the scene separator establishes a segmentation mapping model based on the loaded parameters through a square cabin projection adaptation unit, segments the virtual driving scene into a front path, a rear path, a left path and a right path, and adapts to initial projection pictures corresponding to a projection bearing surface; s3, respectively carrying out geometric correction on the four paths of initial projection pictures by a picture correction module, eliminating distortion caused by a projection angle, and obtaining four paths of corrected projection pictures; s4, if the projection pictures of the adjacent projection bearing surfaces have the visual connection requirement, an edge fusion unit of the picture correction module sets an overlapping region for the edges of the adjacent pictures and carries out brightness equalization processing; and S5, the scene separator transmits the processed four-way projection picture signals to a projector for projecting the received corrected four-way projection picture to the corresponding square cabin projection surface to form a seamlessly connected immersive virtual driving visual environment. According to the invention, hardware purchase and installation costs are reduced, picture distortion is avoided, the lateral image is closer to a real scene, and the driving experience of an immersive visual environment is improved.

The invention provides a double 3D TOF-based projector curved surface automatic correction method and system and a medium, and the method comprises the steps: synchronously collecting the point cloud data of a to-be-projected curved surface based on a double 3D TOF sensor, and obtaining the three-dimensional point cloud data; removing outer points based on an RANSAC (Random Sample Consensus) algorithm, and performing point cloud scale unification by adopting a weighted least square method; based on an improved ICP algorithm, depth and normal features of the complete curved surface three-dimensional point cloud are extracted, and curvature and concave-convex distribution key parameters of the curved surface are calculated; constructing a global pixel-three-dimensional coordinate mapping table, and optimizing edge compensation parameters by adopting weighted B-spline surface fitting; according to the global pixel-three-dimensional coordinate mapping table and the optimized edge compensation parameters, a projection picture is driven to be adjusted in real time, and a curved surface projection correction result is obtained; through automatic point cloud acquisition, modeling and correction, point cloud scale unification and curved surface fitting, curved surface edge compensation is realized, and correction precision is improved.

Embodiments provide for improved computer modeling are provided. A three-dimensional (3D) base mesh corresponding to at least a portion of a character and a 3D feature mesh corresponding to a feature of the character is accessed. One or more portions of the 3D feature mesh are deformed using surface projection based on an overlapping region for the 3D base mesh and the 3D feature mesh to generate a first modified 3D feature mesh. At least one of a texture or normals of the first modified 3D feature mesh is modified based on at least one of a texture or normals of the 3D base mesh to generate a textured 3D feature mesh. An image is rendered based on the 3D base mesh and the textured 3D feature mesh.

The invention relates to a microsphere polishing simulation uniformity evaluation method and device and electronic equipment, and the method comprises the steps: carrying out the projection coordinate plane division of at least one orthogonal coordinate surface of a target microsphere, so as to obtain a rectangular grid region of a target area; performing full-period dynamic simulation on the target microsphere to extract and convert three-contact-point space trajectory coordinates, and generating a space spherical trajectory point coordinate plane projection according to the three-contact-point space trajectory coordinates and the rectangular grid region; and calculating a distribution uniformity standard deviation value of the coordinate plane projection of the track point, and generating a grinding track uniformity result of the target microsphere according to the uniformity standard deviation value. Therefore, the problems that in the prior art, due to the fact that the coupling effect of simultaneous in-orbit movement of multiple balls in actual grinding is not considered, the deviation between the evaluation result and the actual grinding working condition is obvious, the spherical surface grid division precision is uneven, grid division normalization is lacked, the verification efficiency is low, the cost is high, and the working condition adaptability is poor due to dependence on physical experiments are solved.