13 results about "Surface gradient" patented technology

The invention relates to the field of welding, and discloses a non-standard intelligent customized welding system based on vision and surface gradient, which comprises a visual perception module used for iteratively approaching a workpiece from a preset initial height through a self-adaptive high angle shooting exploration mechanism, and combining layered grid division based on a camera view and a progressive multi-angle expansion scanning mode, collecting multi-view three-dimensional point cloud data of the workpiece; and the point cloud processing module is used for performing regional progressive registration on the multi-view three-dimensional point cloud data, implementing threshold constraint based on point cloud curvature characteristics by dynamically adjusting registration step length, and eliminating accumulative errors in combination with pose map optimization. Through self-adaptive high-angle shooting and layered grid scanning, multi-view point cloud can be automatically collected without manually presetting a workpiece model, regional registration and curvature constraint are combined, the workpiece model is constructed, a weld joint structure is automatically extracted based on surface gradient features, traditional manual labeling is replaced, a welding track is generated according to weld joint topology, and the precision is dynamically corrected.

The invention discloses a special-shaped pipe quality evaluation method, system and equipment based on industrial Internet of Things, and relates to the technical field of pipe quality monitoring, and the method comprises the following steps: respectively obtaining end face images of two ends of a corresponding target special-shaped pipe; wherein the cross section of the target special-shaped pipe is oval, a strip-shaped groove is formed in the outer wall of the target special-shaped pipe in the axial direction of the target special-shaped pipe, and a plurality of blind holes are formed in the outer wall of the target special-shaped pipe in the axial direction of the target special-shaped pipe; according to the two end face images, the bottom face gradient of the strip-shaped groove is obtained; obtaining the radial deformation degree of the target special-shaped pipe according to any end face image; acquiring pressure data corresponding to the plurality of blind holes, and acquiring the depth non-standard rate of the blind holes according to the plurality of pressure data; according to the bottom surface gradient, the radial deformation degree and the depth non-standard rate, obtaining a quality evaluation score of the target special pipe; according to the quality evaluation score, whether the target special-shaped pipe is qualified or not is judged, and the method has the advantage that the quality detection accuracy of the special-shaped steel is improved.

The invention discloses a flexible circuit board warping degree non-contact detection method and system, and the method comprises the steps: carrying out the multi-angle scanning of a target flexible circuit board, and obtaining three-dimensional point cloud data; separating a component area and a circuit board substrate area based on a deep learning algorithm, and constructing a circuit board substrate three-dimensional model; a reference reflecting plate is arranged at the bottom of the three-dimensional model, relative spatial position parameters of a reference plane and the detection device are obtained in real time, and a circuit board three-dimensional substrate model is constructed; constructing a self-adaptive coordinate system, and mapping the three-dimensional substrate model of the circuit board into a reference plane coordinate system; curvature parameters of all nodes of the three-dimensional model are calculated through differential geometric analysis, and a curved surface gradient tensor field is constructed; and obtaining a maximum warping amount, a regional warping gradient value and an overall warping degree distribution parameter. The method has the advantages that the warping degree of the circuit board is accurately evaluated through three-dimensional scanning, a deep learning algorithm and differential geometric analysis, and the method has the advantages of high precision, full automation and quick response.

The invention discloses a mining roadway roof deformation monitoring method and system based on a sensor, and relates to the technical field of deformation monitoring, and the method comprises the steps: obtaining three-dimensional point cloud data containing rock mass structure features; separating the rock mass bulge area from the roof main body area; a reference plane is arranged below a roof body area, relative spatial position parameters of the reference plane and a roof body are obtained in real time through a TOF sensor, and a roof three-dimensional model is constructed; mapping the top plate three-dimensional model into a reference plane coordinate system; curvature parameters of all nodes of the roof three-dimensional model are calculated through differential geometric analysis, and a curved surface gradient tensor field is constructed; and based on the curved surface gradient tensor field, obtaining a maximum sinkage, a regional deformation gradient value and an overall deformation distribution parameter, and generating a roof stability evaluation report. The method has the advantages that a more comprehensive, accurate and reliable roof stability evaluation report is provided, and a more accurate safety early warning basis is provided for the mining industry.

The invention provides an online visual detection method and device for flaws of high-speed moving cloth, and relates to the technical field of cloth flaw detection.The online visual detection method comprises the steps that firstly, a response diagram is obtained through time-sharing exposure, a normalized surface gradient modulus is calculated through a normalized difference ratio and logarithm compression, and color albedo interference is eliminated; curvature features are extracted by calculating the absolute value of a Hessian matrix and the square of a Laplacian operator and combined to generate a mixed curvature tensor, and tiny deformation is accurately captured; then manifold unsupervised reconstruction is carried out based on a Gaussian weighted model of a hollowed-out center pixel to obtain an ideal reconstruction tensor, and sample-free adaptive prediction is realized; difference is calculated, a local signal-to-noise ratio abnormal response index is obtained through local statistical window standard deviation normalization, and texture roughness interference is removed; and finally, positioning flaws, carrying out double-threshold judgment by calculating a flaw structure characteristic value and a flaw oil stain characteristic value, and outputting flaw coordinates and categories.

The present application proposes a monocular non-contact fingerprint perspective distortion correction method, which includes: acquiring a non-contact fingerprint image, preprocessing the non-contact fingerprint image, obtaining a preprocessed image and a mask; inputting the preprocessed image and mask into a gradient estimation network, and outputting a predicted surface gradient value; restoring the gradient value to its original size by bilinear interpolation to obtain a normal gradient value; reconstructing the depth map using the normal gradient value to obtain a three-dimensional finger model; and unfolding the non-contact fingerprint image according to the three-dimensional finger model for distortion correction. The present application solves the technical problem that the perspective distortion caused by projection imaging reduces the non-contact fingerprint recognition rate. By performing three-dimensional reconstruction and perspective distortion correction on a single non-contact fingerprint image, no complex acquisition equipment or multiple acquisition results are required, which greatly reduces the requirements for device hardware, improves the recognition performance of non-contact fingerprints, and is more suitable for actual production and life.

This application relates to a method, system, device, storage medium, and computer program for complex near-surface shallow velocity modeling. The method includes: acquiring preset shot-receiver surface elevation, shot line spacing, and receiver line spacing; smoothing the preset shot-receiver surface based on the shot line spacing and receiver line spacing to obtain a first updated surface at different smoothing scales; smoothing the acquired total static correction to obtain low-frequency static correction and high-frequency static correction; smoothing the first updated surface based on the low-frequency static correction and high-frequency static correction to obtain a first simulated surface; constructing an initial near-surface gradient model based on the first arrival time of each seismic trace, the preset shot-receiver surface elevation, and the first simulated surface, and performing iterative inversion using wave tomography to obtain a final velocity model; and using the final velocity model to perform velocity analysis on each seismic trace to obtain seismic data characteristics. This method improves the accuracy of near-surface velocity modeling and reduces near-surface velocity modeling errors.

The invention provides an ornament arrangement method. The method comprises the following steps: acquiring geometric information of a target three-dimensional model; calculating a surface gradient vector of each vertex based on a position relationship between each vertex of the target three-dimensional model and an adjacent vertex of the target three-dimensional model; calculating a nearest neighbor distance between each vertex and an adjacent vertex thereof, and generating a scaling factor according to the nearest neighbor distance; obtaining a decoration model; and determining the orientation of the ornament model according to the surface gradient vector, and determining the size of the ornament model according to the scaling factor, thereby instantiating and arranging the ornament model to the surface of the target three-dimensional model. By accurately calculating the surface gradient vector and the nearest neighbor distance of each vertex, the geometric feature change of the surface of the target three-dimensional model can be intelligently sensed, so that accurate matching of the orientation of the ornaments and the geometric structure of the surface is realized, and the problems of disordered direction, excessive overlapping or non-uniform distribution of the ornaments are effectively avoided.

The invention discloses a goaf collapse tower deformation evaluation method based on an RF-SVM. The method comprises the steps that 1, the surface gradient, the coal seam inclination angle, the mining depth and thickness ratio, the goaf length, the mining layer number, the coal seam spacing and the horizontal distance between a tower and a maximum settlement point are selected to form an original evaluation factor system; step 2, performing normalization and standardization preprocessing on each piece of data; 3, determining the weight of each feature factor; 4, the screened evaluation factors are used for training an SVM model; step 5, performing prediction by using the trained SVM model; the problem that the disasters are difficult to accurately and timely discover and prevent by the traditional monitoring means is solved.

The invention provides a concrete slump detection method and system for a discharge port of a concrete mixer, and the method comprises the steps: obtaining a video image sequence of a discharge port region, extracting spatial-temporal feature points from continuous video frames, carrying out the matching of a feature descriptor fusing local binary pattern texture and motion historical information, and generating an initial displacement vector field; local decomposition is carried out on the initial displacement vector field, abnormal matching points are eliminated according to a hydrodynamic incompatibility threshold value of velocity divergence and rotation, and a sparse matching flow field is obtained; constructing a geodesic line active contour model guided by the sparse matching flow field, and iteratively segmenting a concrete edge contour; taking the edge contour as a boundary, taking a velocity vector of the sparse matching flow field as a surface gradient, adopting a Poisson reconstruction algorithm to construct a three-dimensional surface model of the concrete accumulation body, and based on the projection area, the centroid height and the volume of the three-dimensional surface model, and combining a pre-calibrated mapping relation between geometric characteristics and slump, calculating the slump of the concrete accumulation body. And determining the concrete slump value.

A method for forming a surface having anisotropic friction properties by numerically controlled milling is disclosed. [Solution] In this method, machining simulations of milling are performed for combinations of multiple tool orientation parameters, and a height matrix is ​​constructed from the obtained three-dimensional point cloud data. Then, the contact region is extracted, the surface gradient and gradient amplitude values ​​are calculated, and the sets of gradient amplitude values ​​at the contact leading edge during forward and reverse sliding are extracted. Furthermore, the coefficient of friction for forward and reverse sliding is calculated, and an anisotropy evaluation index is calculated based on these. In addition, an anisotropy evaluation index heat map is created, and a ridge line indicating the direction of sensitivity to changes in the anisotropy evaluation index is generated, thereby enabling quantitative prediction and evaluation of the surface friction behavior. This makes it possible to inversely calculate tool orientation parameters under predetermined cutting parameters based on the anisotropy requirements related to the surface micromorphology. By performing milling according to the parameter combination obtained by this method and predetermined cutting parameters, a viscoelastic material workpiece that satisfies the requirements for friction characteristics or sealing function according to the sliding direction can be obtained. The present invention is useful in satisfying the requirements for friction characteristics and sealing function according to the sliding direction in a seal pair.

The invention discloses a three-dimensional surface reconstruction method and device based on a visual tactile image, and the method comprises the steps: obtaining a to-be-detected visual tactile image of a target object through a visual tactile sensor; for any target pixel point in the visual tactile image to be detected, obtaining normalized coordinates and RGB (Red, Green and Blue) information of the target pixel point; performing position feature enhancement processing on the normalized coordinates of the target pixel points to generate a multi-frequency position vector; splicing the multi-frequency position vector with the RGB information to generate enhanced features; on the basis of the enhanced features, predicting a gradient field by using a lightweight network structure, and generating a surface gradient corresponding to the target pixel point; and reconstructing a three-dimensional surface topography graph based on the surface gradient corresponding to each target pixel point. According to the method, feature enhancement processing and a lightweight network structure are combined, and a synergistic effect of input end high-frequency information enhancement and network end high-efficiency expression capability is realized, so that the calculation amount and the parameter amount can be reduced, and meanwhile, the reconstruction precision of a three-dimensional surface can be improved.

The invention discloses an automatic task allocation method and device based on a DEM technology, equipment and a medium, and belongs to the technical field of geophysical exploration processing of petroleum. According to the method, elevation information in the DEM technology is used for comprehensively calculating the distance, elevation, surface gradient and relative gradient between task points, the score of each other task point is determined, and the task points are distributed through a k-means clustering algorithm; the invention further provides a device for implementing the method, computer equipment and a computer readable storage medium. The method can automatically and reasonably distribute tasks, reduces errors caused by manual distribution, saves time cost and labor cost of constructors, and can be applied to geophysical exploration of petroleum.