90 results about "Shape reconstruction" patented technology

The invention discloses a submarine cable shape monitoring method based on an ultra-weak fiber bragg grating, which comprises the following steps of: obtaining curvatures # imgabs0 #, # imgabs1 # and # imgabs2 # in X-axis and Y-axis directions from curvatures in two orthogonal directions of curvatures calculated by three uniformly distributed optical fibers, representing angle offset from an ith sensing unit to an X-axis positive direction, and obtaining a bending curvature, an arc angle and a direction angle; and coordinate information in the space is further obtained by combining rotation and translation matrix iterative calculation of a shape reconstruction algorithm, namely, three-dimensional space coordinates of the measured curve can be determined point by point, and finally, complete shape reconstruction and other steps are realized. According to the invention, high-precision large-scale three-dimensional deformation monitoring can be realized. By optimizing the eccentric distance and the strain transmission efficiency of the optical fiber, the tiny deformation of the submarine cable is accurately captured, and by combining an innovative three-dimensional curve reconstruction algorithm, the bending, inclination and other deformation states of the cable can be accurately reflected in different environments. Therefore, the method has obvious advantages in a monitoring task with a high-precision requirement, especially in a complex marine environment.

The invention discloses an evaluation and improvement method and device for a tunnel blasting effect and a medium, and relates to the technical field of tunnel engineering.The evaluation and improvement method comprises the steps that a tunnel coupling data set is collected, space registration and three-dimensional shape reconstruction are conducted, fracture space distribution is formed, risk probability mapping is conducted on the fracture space distribution, and a fracture risk thermodynamic diagram is output; the fracture risk thermodynamic diagram and tunnel rock mass data are input into a digital twin blasting model, a load mapping layer carries out load gradient distribution, a rock mass response deduction layer carries out stress wave propagation simulation and damage accumulation quantification, an optimized blasting number instruction set is generated, and a drill jumbo is driven to execute blasting operation and vibration monitoring according to the optimized blasting instruction set. And actual blasting effect parameters are obtained. According to the method, accurate simulation of geological conditions and optimal adjustment of blasting parameters are realized through the digital twin blasting model, and meanwhile, refined and interpretable evaluation of the blasting effect is realized through vibration monitoring and error propagation modeling of the actual blasting effect.

The invention discloses an optical fiber three-dimensional shape sensor based on an optical frequency domain reflection technology and an application method of the optical fiber three-dimensional shape sensor, the optical fiber three-dimensional shape sensor comprises a base material and more than three optical fibers, and all the optical fibers are spirally wound and fixed on the surface of the base material at equal intervals and constant screw pitches to form distributed sensing units; according to the application method, measurement signals of all the optical fibers are obtained, and axial strain and strain are calculated; calculating the total curvature vector of the reconstruction curve of the measured object; calculating a bending direction angle and a curvature of the reconstruction curve of the measured object; performing differential calculation on the bending direction angle to obtain the torsion rate of the reconstructed curve of the measured object; and reconstructing the three-dimensional shape of the measured object according to the curvature and the torsion of the reconstructed curve of the measured object. The invention aims to realize synchronous measurement of bending, torsion and axial strain by using a distributed sensing unit formed by a multi-fiber structure which is spirally wound at the same interval and at a constant screw pitch.

The invention discloses a non-contact local curvature measurement method and system based on a computational metasurface, and the method comprises the steps: S1, phase modulation: carrying out the phase modulation of an incident light field carrying the information of a to-be-measured object through an optical computational metasurface, so as to generate transverse displacement light field distribution related to the contour of the to-be-measured object; s2, signal extraction: separating and extracting a first-order differential signal carrying the edge information of the object to be measured by using a biorthogonal polarization filtering system; s3, reconstructing a three-dimensional shape: reconstructing the three-dimensional shape of the object to be measured according to the first-order differential signal; and S4, curvature calculation: calculating the curvature radius of any local part of the object to be measured according to the three-dimensional shape. The optical calculation metasurface is combined with a biorthogonal polarization filtering system, differential operation of a light field is achieved, the edge contour of an intensity object and the three-dimensional shape of a phase object can be obtained without difference, and therefore non-contact and high-precision measurement of the curvature of the object is achieved, the problem of physical damage of traditional contact type measurement is solved, and the measurement accuracy is improved. And the detection efficiency and adaptability are improved.

The invention relates to the technical field of structural deformation shape reconstruction, in particular to a novel inverse finite element deformation reconstruction method based on virtual deformation field physical constraint. According to the method, a virtual displacement field obtained by sparse strain through inverse finite element reconstruction is used as a strain extrapolation physical constraint; and an iteration thought is adopted, extrapolated strain and measured strain are used for inverse finite element deformation reconstruction again, a new virtual displacement field is obtained, and therefore strain extrapolation can be restrained again. And continuously iteratively reconstructing virtual deformation and extrapolation strain in this way, and finally reconstructing real structural deformation. And determining the accuracy rate of the deformation characterization values based on a plurality of actually measured actual deformation characterization values and a plurality of deformation characterization values determined by the extrapolation strain data, and determining the deformation reconstruction state based on the accuracy rate. According to the method, the strain measurement points are extrapolated through iteration in the deformation reconstruction process, and the virtual displacement field is used as physical constraint, so that the accuracy of deformation reconstruction is improved.

The invention discloses a new error truncation-inverse finite element deformation reconstruction method based on sparse strain data, and relates to the technical field of structural deformation shape reconstruction. Through error truncation of a strain missing sampling area, a deformation hypothesis theory is introduced, lateral shear strain is ignored, a conversion matrix between an inverse finite element reconstruction solution and a real structure solution is established, a dummy deformation field function is substituted into a matrix relational expression between the inverse finite element reconstruction solution and the real structure solution, and the transformation matrix is obtained. Establishing a matrix solution equation between an inverse finite element reconstruction solution and a dummy deformation field function coefficient, directly solving according to input sparse strain data to obtain an optimal dummy deformation field function coefficient, and substituting the field function coefficient back into a dummy deformation field function to obtain real deformation of the structure; according to the new error truncation-inverse finite element deformation reconstruction method based on the sparse strain data, the matrix relation between the inverse finite element reconstruction solution and the real solution of the structure is constructed, the theoretical format is simple, and the applicability is high.

The invention provides a semiconductor device part surface micro defect image preprocessing data processing method and system, and relates to the technical field of data processing, and the method comprises the steps: carrying out the image quality normalization processing of an obtained high-magnification amplification surface original image, and generating a quality enhancement image; performing defect feature selective enhancement processing on the quality enhanced image to generate a feature optimized image; performing three-dimensional shape reconstruction on the feature optimization image to generate surface three-dimensional shape topological data containing height information; on the basis of the surface three-dimensional topography topological data, a topography reference origin is determined at the highest point of a local topography protrusion of the preliminary defect candidate area, and a first feature radiation vector and a second feature radiation vector are generated in a fitting mode from the topography reference origin in the main direction and the normal change gradient direction of the surface texture respectively; according to the invention, precise characterization of micro defects in a high-magnification magnification scene can be realized, and the accuracy and real-time performance of defect detection are guaranteed.

The invention belongs to the technical field of cigarette production, and provides a cigarette three-dimensional shape reconstruction method and system based on laser three-dimensional scanning and application, and the method comprises the steps: collecting three-dimensional point cloud data of the whole surface of a cigarette based on a laser triangular reflection principle; preprocessing the three-dimensional point cloud data by adopting a multi-stage filtering algorithm strategy to obtain reference data; the method comprises the following steps of: dispersing reference data into a plurality of two-dimensional sections along the axial direction of a cigarette, synchronously extracting upper and lower semicircular feature points of the cigarette in different two-dimensional sections by adopting a multi-thread technology, performing offset vector calculation and mirror image translation transformation so as to reconstruct a plurality of continuous two-dimensional reference sections in a virtual space, and performing curved surface reconstruction on the continuous two-dimensional reference sections, obtaining a three-dimensional shape model of the cigarette; based on the three-dimensional shape model, the perimeter and the length of the cigarette are extracted through a mixed measurement model. The cigarette shape detection efficiency can be improved, and the detection accuracy and the data accuracy are improved.

The invention discloses a multi-particle three-dimensional shape reconstruction method based on projection consistency. According to the method, a three-angle laser interference particle imaging system is used for collecting out-of-focus images of three visual angles, a center M * N pixel range is cut to obtain an out-of-focus speckle image, phase recovery algorithm reconstruction is carried out, a two-dimensional particle shape is obtained, a gray threshold value above 70 is set to be a target contour area, binarization segmentation is carried out, and a target contour image is obtained. And smoothing the target contour area. And carrying out three-dimensional space projection on contours of the four candidate results in Matlab, generating a three-dimensional structure in an intersection region, re-projecting the three-dimensional structure to each view angle, calculating an error S between a re-projected image and an original input projection, and selecting a final reconstruction result with the minimum S. According to the method, through systematic iterative optimization and an error evaluation mechanism, trivial fuzzy interference in a phase recovery process is effectively eliminated, and high-precision reconstruction of a multi-particle three-dimensional shape is realized.

The invention discloses a pile foundation concrete accurate pouring control system and method based on multi-source sensing fusion. The pile foundation concrete accurate pouring control system comprises a sensing layer and a control layer, wherein the sensing layer comprises a phased array ultrasonic probe, a binocular vision sensor and a laser ranging array; the modeling layer comprises a three-dimensional hole shape reconstruction module and a BIM digital modeling engine; the data layer comprises a real-time monitoring database and a multi-source data fusion center; the decision-making layer comprises a concrete dynamic evaluation model and a BIM visual platform; the execution layer comprises a self-adaptive PID controller used for adjusting the concrete pumping rate according to the decision instruction, and a three-dimensional visualization terminal used for displaying the BIM model with the tolerance zone in real time. According to the method, a BIM model containing dynamic compensation is constructed through ultrasonic three-dimensional scanning, closed-loop control is achieved by fusing multi-source sensing data, and tolerance band penetration early warning and self-adaptive PID adjustment are combined. The hidden defect discovery rate is improved, and the comprehensive construction efficiency is improved.

The invention discloses a steel plate cutting method and device, a medium and equipment, and belongs to the field of cutting. According to the method, three-dimensional coordinates of all points on the surface of the head of a steel plate are generated by obtaining real-time motion parameters of the steel plate and the head distance and angle detected by a millimeter-wave radar and combining a preset coordinate conversion model. And then, converting the three-dimensional coordinates into a steel plate head shape image by using a morphological reconstruction model constructed based on preset three-dimensional point cloud data and morphological feature extraction rules. According to the steel plate cutting method and device, accurate positioning and efficient cutting are achieved, the production efficiency and the material utilization rate are improved, and the problem that the steel plate cannot be accurately cut in the prior art is effectively solved.

The invention discloses a method for quantitatively evaluating the three-dimensional shape of a thinning defect in a plate under ultrasonic guided wave field undersampling scanning, belongs to the field of industrial nondestructive testing, and particularly relates to high-precision three-dimensional shape reconstruction and thickness loss quantification of a corrosion defect in a metal plate shell structure (such as aerospace skin, a pressure vessel wall, an oil pipeline and the like). According to the method, sparse sampling guided wave field reconstruction, full waveform inversion (FWI) and priori knowledge constraint are fused, Shannon sampling theorem limitation is broken through, efficient measurement of corrosion depth, contour and distribution under the conditions of a single excitation source and a limited view angle is achieved, and the method is suitable for rapid online detection in a complex industrial environment.

The invention relates to the technical field of defect detection imaging, and discloses a high-precision three-dimensional imaging method and system based on continuous magnetic flux leakage data. Collecting surface magnetic flux leakage signals of a measured target to form an initial signal set, and extracting feature vectors by using a convolutional neural network model; separating three-dimensional space data, and obtaining initial three-dimensional position coordinates of the defect through an iterative mapping algorithm; mining spatial geometric features, determining potential geometric boundaries, and fusing data to construct a refined position model; extracting a detection subset, correcting a shape error, constructing a space reconstruction grid, filling holes, and obtaining a complete three-dimensional shape representation; and through precision calibration and signal matching verification, a high-precision three-dimensional image is output. According to the method, the defect positioning and shape reconstruction precision can be effectively improved, the imaging integrity and accuracy are guaranteed, the problems of fuzzy positioning and shape distortion of traditional magnetic flux leakage imaging are solved, and the defect detection requirements of a complex detected target are met.

The application discloses a kind of based on parameter mapping mechanism's unmanned aerial vehicle cluster shape reconstruction method, belongs to unmanned aerial vehicle fleet autonomous decision control technical field, including establishing unmanned aerial vehicle cluster model and unmanned aerial vehicle single body model;Establish the basic behavior rule of unmanned aerial vehicle, including motion trend adjustment and dynamic position adjustment;Set cluster macro shape, according to the unmanned aerial vehicle cluster model and unmanned aerial vehicle single body model established by macro shape parameter mapping to micro rule parameter, determine neighborhood range, according to the basic behavior rule of unmanned aerial vehicle established, generate cluster macro three-dimensional shape, and the generated cluster macro three-dimensional shape is with preset shape Accuracy analysis, according to accuracy result completes unmanned aerial vehicle shape reconstruction.The application uses the above method, can make operator directly modify macro shape parameter to directly adjust the relative distance between unmanned aerial vehicle cluster machines, to form preset macro shape in three-dimensional space.

The present application relates to the technical field of image data processing, in particular to a missing tooth shape intelligent reconstruction method based on contralateral tooth mirror image transformation. According to the patient's masseter axial ultrasound image and temporal muscle axial ultrasound image, the robustness of each side of the masticatory muscle of the patient's both cheeks is determined; the average wear degree of each side of the patient's both cheeks is measured, and then a regression equation of the average wear degree and the robustness is constructed; the coordination coefficient between the missing tooth side and the contralateral side of the patient is determined by using the regression equation, and then it is judged whether the contralateral homonym tooth of the missing tooth needs to be corrected; if correction is needed, the wear degree correction coefficient of the contralateral homonym tooth is constructed, and then the contralateral homonym tooth of the missing tooth is corrected, and the missing tooth shape reconstruction is carried out based on the corrected contralateral homonym tooth. The present application corrects the contralateral homonym tooth of the missing tooth, so that the missing tooth shape reconstruction is more consistent with the dynamic coordination of masticatory movement.

System, methods, and other embodiments described herein relate to single-shot multi-object three-dimensional (3D) shape reconstruction and categorical six-dimensional (6D) pose and size estimation. In one embodiment, a method includes inferring a heatmap based upon a feature pyramid, where the feature pyramid is generated based upon a red green blue depth (RGB-D) image that includes objects. The method further includes sampling a 3D parameter map at locations corresponding to peaks in the heatmap, where the 3D parameter map is inferred based upon the feature pyramid, and where the locations include latent shape codes, 6D poses, and one-dimensional (1D) scales. The method further includes generating point clouds based upon the latent shape codes, the 6D poses, and the 1D scales.

The invention discloses a low-coherence interference microstructure rapid measurement method based on an FPGA, and the method comprises the steps: enabling the FPGA to respectively receive image data and single-point light intensity data collected by a CMOS sensor and a photoelectric detector, and transmitting the two types of data to an FPGA chip internal memory; a parallel pipeline architecture of the FPGA is designed, so that interference pattern contrast can be calculated in real time and displacement point-by-point calculation can be completed while a series of image data and photoelectric detector interference analog signals are received, and the processing efficiency is remarkably improved; and calculating the position of an interference envelope peak value by adopting a gravity center method, completing three-dimensional shape detection of the microstructure, and realizing three-dimensional shape reconstruction. According to the method, the processing speed of low-coherence interference measurement can be effectively increased, the microstructure morphology can be restored at a high speed, and online detection application of low-coherence interference in the fields of semiconductor packaging, lithium battery manufacturing, ultra-precision machining and the like is facilitated.

The invention relates to the field of tongue image three-dimensional shape analysis, in particular to a tongue image three-dimensional shape reconstruction method based on multi-source sensor fusion. The advantages of multi-source sensors such as a structured light depth camera, a high-resolution RGB camera, a polarization filter, a near-infrared camera and a high-speed TOF camera are fused. High-precision tongue image three-dimensional point cloud is collected through a structured light depth camera, and the geometric dimension of the tongue image is accurately described; a high-resolution RGB camera is used for complementing tongue image textures, and the problem of light reflection is solved by combining a polarization filtering technology; the near-infrared camera supplements tongue root and surface blood vessel texture information; and the high-speed TOF camera monitors the tongue image in real time and compensates the motion blur error. And finally, fusing data acquired by a multi-source sensor, and performing three-dimensional grid reconstruction to obtain a complete and high-quality three-dimensional tongue image model.

The invention provides an optical fiber shape sensing system, method, medium and equipment, in the system, a sensing unit comprises a multi-core optical fiber, the multi-core optical fiber is provided with at least three eccentrically distributed sensing cores and a central core, each sensing core is inscribed with a fiber bragg grating used for sensing axial strain caused by bending and torsion, and the central core is provided with a fiber bragg grating used for sensing the axial strain caused by bending and torsion. The central core is used for providing temperature compensation reference; the signal processing unit is used for receiving the original wavelength and strain data acquired by the sensing unit and executing filtering, temperature compensation and curvature and torsion calculation processing; and the shape reconstruction and display unit reconstructs a three-dimensional space curve through numerical integration based on the geometric parameters output by the signal processing unit, and realizes real-time visual display of a three-dimensional shape. According to the invention, high-precision and high-stability optical fiber shape sensing can be realized in a complex dynamic scene, and application requirements of complex scenes such as medical catheter navigation and flexible robot control can be met.

The invention relates to the technical field of biomedical engineering, and provides a tongue body motion form reconstruction and neuromuscular lesion recognition method, which comprises the following steps: S1, acquiring a multi-modal original signal by using a flexible electrode array attached to a lingual surface, and recording a system timestamp; s2, performing targeted filtering, artifact removal and feature extraction processing on the multi-mode original signal; s3, reconstructing a local dynamic curved surface of the lingual surface by adopting a preset model, and inferring an overall position and posture sequence of the tongue body in combination with an IMU signal; s4, a joint optimization objective function is constructed, and a tongue body three-dimensional dynamic form sequence is obtained through iterative solution; s5, performing motion unit action potential MUAP decomposition and feature extraction on the surface electromyogram signal sEMG; and S6, constructing lesion feature vectors based on the multi-dimensional abnormal features, and analyzing and generating a tongue lesion risk map TDM through a machine learning model. The defects that real motion reconstruction, form inference and neuromuscular lesion positioning of the tongue cannot be achieved through an existing tongue detection technology are overcome.

The application discloses a kind of irregular particle shape reconstruction methods based on phase recovery, builds interference particle imaging system;In defocus image plane obtains the defocus speckle image I of irregular particle to be measured M ; The defocus speckle image I M It is sheared, and the speckle region image I located in the center position and the size of N×N after shearing is retained;Speckle region image I is input into phase recovery algorithm model and iterative calculation is carried out, and preliminary reconstruction result is obtained;Proportion factor factor SF is set, and the preliminary reconstruction result of the above iteration, i.e. new particle estimate p k+1 (x0,y0) is scaled with proportion factor SF, and final reconstruction particle shape is obtained.Compared with prior art, the application can directly obtain accurate shape information of irregular particle through particle interference defocus image, without additional optical path setting, and the device is simple, which provides basis for the measurement of complex particle field.

The invention belongs to the related technical field of optical microscopic measurement, and discloses a continuous scanning structured light three-dimensional shape measurement method and system based on axial gradient screening, and the method comprises the steps: carrying out the illumination scanning of a to-be-measured sample through a continuous vertical structure, projecting a preset stripe pattern to the to-be-tested sample at each axial position and acquiring a structured light image; calculating the axial gradient values of the light intensity of all pixel points in the structured light images about the axial position, and screening the structured light images with the maximum axial gradient value greater than a first preset threshold value to form an effective image stack; and carrying out secondary screening on the light intensity data of the pixel points according to the axial gradient square value so as to carry out three-dimensional shape reconstruction measurement. According to the method, the structured light image is screened by using the axial gradient value, and secondary screening is performed on the light intensity data based on the axial gradient square value, so that the redundant data volume is reduced, the calculation efficiency is improved, and efficient measurement of a large-axial-range sample is realized on the premise of ensuring the precision.

The invention relates to the technical field of rail shape monitoring, in particular to a rail deformation sensing method and device based on a flat-ribbon optical cable. The device is characterized by comprising a bandlet optical cable, a conduction optical fiber, a demodulator and a computer, a fiber bragg grating array which is weak in reflectivity, determined in grating distance and capable of being calibrated in position is accurately inscribed in two optical fibers in the flat-ribbon optical cable, interference of temperature fluctuation and axial strain is effectively eliminated through double-optical-fiber cooperative measurement and differential calculation, and when a rail is subjected to sedimentation or bending deformation under the action of train loads and environmental factors, the fiber bragg grating array is accurately inscribed in the flat-ribbon optical cable. Deformation is synchronously transmitted to the bandlet optical cable and causes the wavelength change of the reflection center of each fiber bragg grating, a wavelength change signal is transmitted to the demodulator through the conduction optical fiber to be demodulated in real time and output to the computer, and the computer is based on a wavelength-strain-curvature mapping relation and combines a Freen-Serret shape reconstruction and vertex error correction algorithm. The spatial shape reconstruction of the rail is realized, and the settlement height change is output, so that the real-time, continuous and visual monitoring of the settlement process of the rail is realized. The method is suitable for the technical field of rail deformation and settlement monitoring.

The invention provides a substrate deformation measurement system based on a fiber bragg grating (FBG) and a self-adaptive layout method thereof. The substrate deformation measurement system comprises an FBG sensor network, a data acquisition module, a signal preprocessing and data analysis processing module and a visual interface, the FBG sensor network comprises a measured substrate and a fiber grating string; the data acquisition module comprises a tunable broadband light source, an optical isolator, an optical circulator, a signal transmission optical fiber, a spectrum analyzer and a corresponding demodulation algorithm; the signal preprocessing and data analysis processing module comprises hardware equipment and computer software; and the visual interface uses Labview to write a front-end interface, and is used for performing three-dimensional real-time display on a substrate shape reconstruction result and realizing an alarm function for special situations. According to the invention, through fusion of real-time data and a prior model, focusing monitoring and resource optimization configuration of a key area are realized, and the problems of high calculation complexity, low data processing efficiency and the like in a traditional distributed fiber grating morphology sensing technology are solved.

This invention provides a method and system for optical fiber shape reconstruction, comprising: acquiring an optical fiber reference signal and an optical fiber measurement signal; processing the acquired optical fiber reference signal and optical fiber measurement signal respectively to obtain an optical fiber reference spectrum and an optical fiber measurement spectrum; based on the optical fiber reference spectrum and optical fiber measurement spectrum, using a preset deviation calculation algorithm to obtain a wavelength offset including noise; performing noise reduction processing on the wavelength offset using a wavelength offset denoising model to obtain denoised strain information; and reconstructing the optical fiber shape based on the strain information using a shape reconstruction algorithm. This invention provides a method and system for optical fiber shape reconstruction that can achieve good accuracy in reconstructing the three-dimensional shape of optical fibers while effectively improving the speed of three-dimensional shape reconstruction, thus helping to meet the real-time requirements of optical fiber three-dimensional shape reconstruction applications.

A facial texture reconstruction unit reconstructs a texture of a face from a 2D video of a person. A facial shape reconstruction unit reconstructs a 3D shape of the face from the 2D video. A pose estimation unit estimates a pose of the person from the 2D video. A shape integration unit reconstructs a 3D shape of the body corresponding to the estimated pose based on the 3D shape data, and integrates the reconstructed 3D shape of the body and the reconstructed 3D shape of the face to reconstruct a 3D shape of the person. A texture reconstruction unit reconstructs a texture image of the person by blending, with an image of the reconstructed texture of the face, a texture image included in the texture data and a model generation unit generates a 3D model of the person based on the 3D shape and the texture image of the person.

The application discloses a kind of volume calculation and geometric reconstruction methods, devices, equipment and medium inside road disease, which comprises: standardization processing to the three-dimensional simulation point cloud data of inside road disease, to obtain standardization simulation point cloud data;Pretreatment data and identify disease connected sub-region, determine the internal starting point set to construct starting point set, based on starting point set Construction space step direction and step search boundary point, generate boundary point set, fusion boundary point set obtains disease space profile, based on disease space profile completes disease volume calculation and three-dimensional geometric shape reconstruction;Since the application accurately locates the disease boundary by internal starting point constraint combined with multi-direction step search, restores complete disease geometry by fusing boundary points, accurately realizes the topological reconstruction and volume calculation of complex disease network, effectively solves the problem of incomplete disease point cloud boundary and complex topology of internal complex disease of road, and improves the integrity of disease reconstruction and the accuracy of volume calculation.

This disclosure provides a point cloud processing method, apparatus, computing device, and storage medium. The point cloud processing method includes: acquiring object states in an initial point cloud frame; extracting object point clouds from the initial point cloud frame based on the object states; calculating a shape code of the initial point cloud frame based on a shape model and the object point clouds in the initial point cloud frame, wherein the shape code is used to characterize the surface shape of the object; and calculating the object states and / or shape codes of corresponding objects in other point cloud frames of the point cloud sequence based on the shape code and object states of the initial point cloud frame. Embodiments of this disclosure combine object tracking and shape reconstruction based on a shape model, improving the accuracy of object tracking and the fidelity of shape reconstruction.

The invention discloses hub blank detection equipment and a detection method, and belongs to the technical field of automobile engineering.The detection equipment comprises a first station, a second station and a third station, the first station is provided with an identification mechanism for collecting images of hub blanks and obtaining wheel types, characters and valve hole angles of the hub blanks, and the second station is provided with a detection mechanism for detecting the wheel types, the characters and the valve hole angles of the hub blanks. The wheel hub blank is moved to a third station after being detected by the detection mechanism, the third station is provided with an identification mechanism, a marking position is provided through the combination of blank shape point cloud reconstructed by the second station and a clamping point algorithm, and the identification mechanism drives the wheel hub blank to rotate, so that the clamping point is accurately aligned with the marking position; the invention further provides a hub blank detection method. Through close cooperation of the three stations, full-process automatic detection of hub blank recognition, size detection, three-dimensional shape reconstruction, clamping point calculation and physical marking is achieved.

The application provides a tokamak plasma boundary identification and shape reconstruction method. First, the EAST plasma boundary is identified by using a U-Net full convolutional neural network, then boundary points are selected, and finally, the pixel coordinates of the boundary points are fitted with EFIT through an XGBoost model. The application can convert the boundary from the image plane to the tokamak polar surface, and realize the plasma shape reconstruction based on a monocular visible light camera. According to the experimental results, the algorithm has high reconstruction accuracy, and the average error on the test set is only 7.36 mm.