101 results about "Iterative reconstruction" patented technology

The invention discloses a self-adaptive threshold SAMP reconstruction method for a power quality disturbance signal. According to the method, a compression observation value is obtained by constructing a random Gaussian observation matrix, and sparse representation is carried out on an original signal by using discrete Fourier transform. In the iterative reconstruction process, the spectrum amplitude difference is introduced for the first time to serve as an adaptive termination basis, and automatic adaptation of different noise levels and different disturbance characteristics is achieved in combination with a dynamic threshold update function. According to the method, the problems of traditional SAMP sparseness overestimation and redundant iteration are effectively avoided, and the calculation load is remarkably reduced. Compared with an OMP method, an original SAMP method and the like, the method has the advantages that the number of iterations can be reduced by 30%-60%, the reconstruction signal-to-noise ratio is increased by 2-5 dB, the root-mean-square error is reduced by 10%-25%, higher robustness and real-time performance are achieved in power quality disturbance signal reconstruction, and the method is quite suitable for scenes such as compressed sampling, edge calculation and high-speed signal reconstruction in a power quality monitoring system.

Technology is described for handling truncated data in iterative reconstruction. A method comprises iterating on a volume of an object including a non-truncated part based on image data and at least one truncated part representing deficiently imaged data. The volume is represented by voxels. The iterating includes regularizing the non-truncated part of the volume using a first regularizer, and regularizing the truncated part of the volume using a second regularizer different from the first regularizer.

The invention discloses an image compressed sensing reconstruction method and system based on a recursive diffusion model, and belongs to the technical field of image processing and compressed sensing, and the method comprises the steps: obtaining a to-be-reconstructed original image; performing block compressed sensing sampling on an original image to be reconstructed to obtain a complete observation value; initializing the complete observation value by adopting a pseudo-inverse reprojection operation to obtain an initial reconstructed image; performing complete reconstruction on the initial reconstruction image by using a recursive diffusion model; wherein in the whole image domain, the initial reconstruction image is used as the image estimation of the current iteration, through a lightweight recursion UNet submodule and an operator condition circulation prior submodule in the recursion diffusion model, multi-step iteration reconstruction is carried out, and a final reconstruction image is output. According to the method, a recursive refinement mechanism and stride memory prior are introduced, high-quality image reconstruction is realized under a small number of iteration steps, and the calculation and storage overhead is remarkably reduced.

The invention discloses a building contour accurate extraction method based on prior information and a related device, and the method comprises the steps: obtaining remote sensing image data, carrying out the prior information mining processing of contour extraction on the remote sensing image data, obtaining the contour extraction prior information corresponding to the remote sensing image data, and obtaining the contour extraction prior information of the remote sensing image data; wherein the contour extraction prior information comprises local control prior information and global control prior information; inputting the remote sensing image data and the contour extraction prior information into a building contour extraction reasoning model, and performing iterative reconstruction processing on the remote sensing image data in the building contour extraction reasoning model by taking the contour extraction prior information as coordinated guidance, and outputting the accurate contour mask corresponding to the building in the remote sensing image data. In the embodiment of the invention, remarkable beneficial effects are achieved in the aspects of geometric accuracy, structural integrity and complex scene adaptability of the building contour.

The invention relates to a high-precision multi-surface wavelength tuning interference measurement signal processing method. The core of the method is to solve the problem of dissociation of superposed interference signals and overcome the frequency spectrum fence effect. The patent process comprises the following steps: constructing a dissociation framework based on an iteration vector and a time delay virtual detection point; optimizing an iteration process by using an approximate Newton method; designing a double judgment dissociation criterion and orthogonally outputting a dissociation result; performing frequency spectrum fine segmentation analysis and phase demodulation function extraction on the dissociation signal to realize high-precision solution of harmonic frequency and phase; and the dissociation quality can be evaluated by using a correlation coefficient quantification method. The method can effectively separate multi-surface interference superposition signals and accurately reconstruct key parameters, is obviously superior to a traditional method (such as FFT), and improves the performance by about two orders of magnitude. Experiments prove that the surface shape error is controlled to be 10e <-3 > magnitude, the frequency precision reaches 10e <-4 > magnitude, and the method has excellent robustness and wide applicability and is suitable for high-precision optical element detection.

The invention relates to the technical field of nuclear medicine diagnosis, and particularly provides an ROI image reconstruction method and system based on SPECT data, and the method comprises the steps: reconstructing a coarse scanning image according to large-view coarse scanning projection data; generating ROI image estimation according to the coarse scanning image; performing loop iteration updating on the ROI image estimation until a preset convergence condition is met; the loop iteration updating process comprises the following steps: generating estimated projection data according to ROI image estimation of current iteration; obtaining projection deviation according to the estimated projection data and the small-view fine scanning projection data; obtaining an image state index according to ROI image estimation of the current iteration and the previous iteration; determining a coarse scanning data contribution weight according to the image state index; updating the ROI image estimation of the current iteration according to the projection deviation, the small-view fine scanning projection data, the coarse scanning data contribution weight and the large-view coarse scanning projection data; according to the method, the iterative reconstruction process can adapt to the dynamic change of the image state.

The invention provides a PET-MR joint reconstruction method and system based on an expert network modular regularizer. The method comprises the following steps: constructing a PET-MR joint reconstruction backbone network based on a decoupling iteration framework; s2, constructing and integrating a U-Net joint regularizer for expert network modularization, and integrating the U-Net joint regularizer into the iterative reconstruction framework in the step S1 to obtain a final joint reconstruction network model; applying a comprehensive loss function to supervise an end-to-end learning process of the joint reconstruction network model; constructing a training data set, and performing end-to-end joint training on the joint reconstruction network model by using a loss function; in the reasoning stage, PET and MR measurement data to be reconstructed are input into the trained joint reconstruction network model, and finally a reconstructed PET image and a reconstructed MR image are output. According to the method, the functional metabolism information accuracy of the reconstructed PET image and the anatomical structure detail definition of the MR image are enhanced, and the high feature fidelity of each modal image is ensured, so that the overall quality and clinical diagnosis value of the reconstructed image are improved.

The invention discloses a knowledge base construction method and system based on urban planning implicit knowledge deduction, relates to the technical field of urban planning, and aims to solve the problems that an existing planning knowledge base is insufficient in implicit knowledge mining, poor in scene adaptability and lack of dynamic optimization capability. The method comprises the steps of obtaining multi-source data and performing standardization processing to obtain an enhanced data pool; optimizing the large language model to extract explicit and implicit planning knowledge; constructing a planning knowledge association network with association strength; building an initial knowledge base containing classification, retrieval and implicit knowledge deduction units; generating an adaptability evaluation result through a multi-scene test; constructing a knowledge evolution rule based on an evaluation result and completing knowledge base iterative reconstruction; and establishing a real-time spatial data dynamic triggering mechanism to realize continuous optimization of the knowledge base. According to the method, accurate association and deduction of explicit and implicit knowledge are realized, the scene adaptability and dynamic updating capability of the knowledge base are improved, scientific and efficient knowledge support is provided for urban planning decision making, and the method is suitable for various planning scenes.

The invention relates to a Go-pos scene self-adaptive remote sensing image super-resolution reconstruction system and method, relates to the technical field of space optics, and solves the technical problems that when a traditional algorithm faces a remote sensing image with a complex landform, super-resolution reconstruction fails, the image edge reconstruction effect is poor, initial frame construction is incomplete, and subsequent iteration cannot be supported. The system comprises an input image loading module, a scene recognition module, a degradation model configuration module, an initial reconstruction NEDI module, a POCS iteration reconstruction module, an edge enhancement module and an output and storage module. According to the Go-pos scene adaptive remote sensing image super-resolution reconstruction system and method provided by the invention, a set of remote sensing image super-resolution reconstruction scheme with strong robustness, wide adaptability and excellent detail reconstruction effect is constructed through combination of scene recognition driven adaptive degradation modeling and an edge-oriented reconstruction strategy; and particularly, the method shows higher universality and reconstruction quality in diversified landform scenes.

The present disclosure provides a cone beam computed tomography system for proton therapy comprising an x-ray source configured to generate x-rays and positioned to rotate around a patient at a treatment isocenter, a detector assembly positioned opposite the x-ray source and configured to receive x-rays that have passed through the patient, a rotation mechanism configured to rotate the x-ray source and the detector assembly around the patient while maintaining their relative positions, a translation mechanism configured to translate at least one of the x-ray source, the detector assembly, or a patient couch during rotation to implement a wobbled scan orbit, and a scatter rejection grid attached to the detector assembly and focused on the x-ray source to reduce scattered x-rays. The translation mechanism distributes missing projection data across multiple radii and angles, enabling improved reconstruction quality through iterative reconstruction methods.

The invention discloses a compressed sensing MRI (Magnetic Resonance Imaging) reconstruction method and system based on cross-frame guidance and dual-view interaction enhancement. MRI image pairs are obtained, and image compressed sensing reconstruction is performed by using a network comprising a sampling module, an initial reconstruction module and a plurality of iterative reconstruction modules. Each iterative reconstruction module comprises two branches and a double-view-angle interaction enhancement module, and one branch outputs key frame reconstruction guide information; and the other branch reconstructs the auxiliary frame reconstruction image, and performs adjacent slice joint reconstruction by combining key frame reconstruction guide information. Frequency domain information is reserved by constructing image pairs with different sampling ratios, adjacent slices have high spatial correlation, the cross-frame guide module is used for performing feature interaction and information compensation between the slices with different sampling ratios, the double-view-angle interaction enhancement module is used for enhancing structural continuity from different axial directions, and the structural continuity is enhanced. And the global structure is consistent and details are reserved.

The application discloses a CT image iterative reconstruction method and system based on maximum residual extension projection. The application collects CT original projection data, constructs a linear equation group model, disassembles a reconstruction sub-problem, iteratively selects a work row and column with the maximum residual after initialization of parameters, adopts a phased differentiated extension projection strategy combined with an adaptive step length update solution vector, terminates iteration in combination with multiple convergence criteria, and finally reorganizes a reconstructed image. Meanwhile, optimization strategies such as projection data extension, extended power divergence optimization, multi-domain network constraint and residual prior regularization are configured to adapt to complex working conditions such as truncation, noise, sparsity and limited angle. The application also builds a modular closed-loop reconstruction system to realize full-process automatic operation. The application can accurately correct reconstruction errors, accelerate the iterative convergence speed, effectively suppress various types of artifacts, improve imaging accuracy and robustness, does not require a large amount of training data, is suitable for multiple CT imaging scenes, and has high engineering promotion value.

The invention relates to a magnetic resonance image processing method and device, and an EPI-based image processing method. The method comprises the steps of obtaining a first sampling image of a target object according to sensitivity information of a receiving coil corresponding to the target object and K space data; correcting artifacts in the first sampling image to obtain a second sampling image of the target object; and iterating data of a preset first magnetic resonance image by taking the second sampling image as a constraint condition and taking the K space data as a fidelity term in an iterative reconstruction process to obtain a magnetic resonance image of the target object. By adopting the method, the problem of aliasing artifacts existing in magnetic resonance imaging images can be solved.

The invention relates to the technical field of data processing, and further relates to a data extraction method and system for digital geological mineral exploration. Comprising the following steps: step 1, performing analog-to-digital conversion on multiple paths of original magnetic field response voltage signals synchronously acquired by multiple optical pump atomic magnetometer sensing units to obtain multiple paths of original magnetic field response digital sequences; 2, performing phase gradient field iteration reconstruction processing on the magnetic field in-phase response matrix and the magnetic field orthogonal response matrix to obtain a reconstructed phase matrix and a magnetic field amplitude matrix; and 3, calculating a magnetic field amplitude deviation matrix and a phase deviation matrix according to the magnetic field amplitude matrix and the reconstructed phase matrix, converting the mineral anomaly candidate position into a geological space coordinate, and outputting geological mineral anomaly feature data.

State of the art systems being used for QSM reconstruction have explored prior information from both magnitude and phase data. However, the underlying assumption is that the susceptibility maps and the magnitude images have coinciding edges. Establishing the ground-truth susceptibility maps is difficult and leads to limited applicability of supervised methods. Further, with portable MRI machines becoming a reality, low-field imaging is getting more prominence, which brings in several associated challenges due to noise and external interference. The disclosure herein generally relates to magnetic resonance imaging (MRI) imaging systems, and, more particularly, to a method and system for quantitative susceptibility mapping (QSM) reconstruction in magnetic resonance imaging (MRI) systems. The system performs an iterative reconstruction of QSM, wherein in each iteration the reconstructed QSM from previous iteration is refined by comparing with a reference image generated using same subject's prior MRI data.

The present application relates to the technical field of spectral CT imaging, and particularly relates to a physical parameter-based material decomposition method and device, electronic equipment and medium, the method comprising: calculating at least two groups of different equivalent energy CT projection correction parameters and spectral correction parameters based on known phantom spectral CT pre-scan data and initial equivalent spectrum; correcting a material decomposition model according to the parameters to establish a mapping relationship between CT projection data and base material thickness under corresponding equivalent energy. The corresponding projection data of the to-be-measured phantom is corrected using the projection correction parameters, and the base material thickness data is obtained in combination with the mapping relationship; the base material image is generated through analysis or iterative reconstruction, and the virtual single-energy image is obtained through linear combination, thereby solving the problem of low spectral CT material quantitative analysis precision in the related art and improving the precision of spectral CT material quantitative analysis.

Systems, methods, and apparatuses for image reconstruction. One computer-implemented method includes receiving measurement data representing a subject and generating an image estimate of the subject based on the measurement data. The method also includes refining the image estimate by performing an iterative reconstruction process comprising a plurality of iteration steps, each iteration step comprising (i) computing a data consistency term based on the image estimate and the measurement data, (ii) generating a correction term using a machine learning model based on the image estimate, the data consistency term, the measurement data, and cross-iteration information, and (iii) updating the image estimate based on the correction term, the data consistency term, and a global learning rate corresponding to the iteration step.

This invention relates to the field of medical image reconstruction technology, specifically to a method for reconstructing low-dose CT images of patients with coronary artery disease based on image enhancement. The method includes: acquiring multi-angle raw projection data of low-dose CT images from patients with coronary artery disease; performing statistical noise modeling and signal recovery on the projection data to obtain denoised projection data; generating an initial coronary CT image sequence through an iterative reconstruction algorithm; extracting cardiac structures and completing region segmentation to obtain labeled images; performing region-specific differential image enhancement based on the labeled images; enhancing vessel wall details and extracting calcified plaque features; combining edge-preserving noise suppression with post-optimization; and outputting high-quality low-dose CT reconstructed images. This method effectively improves the noise artifact problem caused by low-dose scanning, preserves key anatomical details and lesion features of the coronary arteries and myocardium, and enhances the clinical diagnostic practicality of low-dose CT images for coronary artery disease.

The present application relates to the technical field of magnetic resonance imaging, and particularly relates to a kind of intelligent sparse low-rank non-cartesian magnetic resonance dynamic imaging method, comprising the following steps: acquiring the magnetic resonance k-space data of non-cartesian continuous sampling using multiple coils, and using frame operator to rearrange the data along time dimension to obtain undersampled k-space data, then the frame after the non-cartesian undersampled k-space data to be reconstructed is input into the network trained to carry out image reconstruction, and the final dynamic image is reconstructed by deep spatio-temporal sparse, time low-rank learning, data consistency verification and loss function constraint.Compared with prior art, the present application uses multiple network feedback iteration to reconstruct image, which greatly speeds up the reconstruction speed of non-cartesian magnetic resonance dynamic image and improves the spatio-temporal resolution.

The application discloses a bridge prestressed pipe grouting compactness detection method, device and equipment, relates to the bridge construction technical field, and obtains the initial slowness vector, and arranges the initial slowness vector into the initial slowness matrix, and the concrete area grid and the pipe area grid in the initial slowness matrix are limited and constrained by the wave speed range of the concrete area to be detected and the wave speed range of the pipe area grouting material, the final slowness vector is obtained by using the iterative reconstruction method SIRT iteration, and the final slowness matrix is formed and imaged to judge the grouting compactness;The process firstly obtains the position of the concrete area and the pipe area, uses the known information as the prior information in the iterative reconstruction method SIRT iteration inversion, limits and constrains the concrete area and the pipe area in the iterative inversion, highlights the position of the grouting pipe, offsets the phenomenon that the wave speed change does not correspond to the defect area in the present stage SIRT inversion, and thus accurately judges the bridge prestressed pipe grouting compactness.

The invention discloses a biased VSP missing data reconstruction method and device based on 2D FFT, electronic equipment and a medium. The method may include: sorting biased VSP data into a plurality of common geophone gathers; constructing a sparse sampling operator for the common detection point gather; and obtaining missing data aiming at the data reconstructed through common detection point gather iteration. The method is suitable for missing data reconstruction of the biased vertical seismic section, data can be effectively complemented, and the influence of insufficient underground illumination caused by the missing data is relieved.

The invention relates to the technical field of computed tomography, in particular to a tomography imaging method and device, tomography equipment and a storage medium, and aims to realize coordinate system alignment of high-resolution and large-view imaging links in a public reconstruction space through a first projection matrix and a second projection matrix constructed on the basis of the same calibration motif. A geometric consistency basis is provided for joint reconstruction of double-source projection data; a projection matrix is fused into a reconstruction residual error minimization process, iterative reconstruction is carried out in combination with image structure regularization constraint, global geometric consistency and local detail fidelity are both considered under the condition that an external high-resolution label is not needed, and the overall image resolution and imaging quality are improved while the large-view imaging capability is maintained.

The invention discloses an iterative image reconstruction method using regularization and equipment thereof. The equipment comprises CT imaging equipment and a computer readable storage medium. The reconstruction method comprises the following steps: acquiring a function relationship between attenuation information of an image and a regular term weight; acquiring attenuation information of each image; calculating based on the attenuation information of each image and the function relationship to obtain a regular term weight corresponding to each image; and performing iterative reconstruction based on the regular term weight corresponding to each image and the projection data to obtain an optimal solution of each image. According to the iterative image reconstruction method using regularization, the regularization term weight of image iterative reconstruction can be adaptively adjusted among the images with different attenuation levels, so that the consistency of the image smoothness of the different images is improved.

The present application relates to the field of new energy power prediction, and proposes an interpretable wind power prediction method based on feature matrix iterative reconstruction, considers the hidden information contained in the model prediction error, mines the maximum path of error generation through the time fusion transformer TFT model with interpretability, dynamically reconstructs the feature matrix, solves the optimal feature matrix, and thus improves the prediction accuracy of the model; the maximum path of error generation is explained from the local and global perspectives respectively, and a traceability mechanism of prediction error is established, so that the present application can effectively improve the safety and reliability of wind power prediction.

The invention relates to an image encryption method based on adaptive compressed sensing and multi-scale feature fusion, which belongs to the technical field of new-generation information, and comprises the following steps: inputting an original image into a computer system, and receiving and identifying the original image by the computer system; in the encryption stage, a computer system processor executes a computer program and executes double encryption operation on an input original image to sequentially obtain an intermediate ciphertext image, a hash key and a final encrypted image, and the computer system processor executes the computer program and compresses the final encrypted image to obtain a compressed ciphertext bit stream; and processing the generated compressed ciphertext bit stream through a competitive iterative reconstruction algorithm in combination with the Hash key, and outputting a decrypted image after high-quality reconstruction.

The invention discloses a predictive surface shape multi-angle rotation iterative reconstruction method and device for monocular phase deflection. The method comprises the steps that a checkerboard calibration plate and a displayer are used for displaying a black and white checkerboard calibration displayer, the position relation of a camera and a world coordinate system and internal parameters of the camera; a coordinate correspondence mechanism between a display screen and a camera is established by writing a sine structured light pattern, and sub-pixel-level matching of a display screen pixel array and camera imaging pixels is realized through double processes of light field modulation and image decoding; based on the predicted surface shape, simulating a predicted surface shape equation and a preset height, and adopting ray tracing to reconstruct a light path; on the basis of a predictive surface shape equation, a preset height and a tracing reconstruction light path, an inclination direction and an angle are added as variables, and PV is taken as a target value to carry out nonlinear optimization so as to obtain an optimal height, an inclination direction and an angle, thereby obtaining a to-be-measured surface shape morphology. According to the invention, the problem of depth information acquisition by a traditional monocular is solved.

The invention belongs to the technical field of ultrasonic detection, and discloses an LTI-SIRT tomography method and system based on chordwise angle wave velocity compensation, and the method comprises the steps: analyzing the influence of wood anisotropy on ultrasonic propagation through constructing an LTI-SIRT algorithm combining linear time-invariant ray tracing and a joint iterative reconstruction technology, so as to determine the correlation between a chordwise angle and a wave velocity, and determining the correlation between the chordwise angle and the wave velocity; healthy layer wave velocity data is obtained through test measurement or theoretical derivation, a chordwise angle wave velocity compensation model is established, and section wave velocity distribution is reconstructed by inputting an algorithm after compensation coefficient correction defect layer ultrasonic propagation time is calculated. According to the method, the problem of ultrasonic propagation errors caused by wood anisotropy is effectively solved, the propagation time data accuracy is improved, the stable wave velocity image is obtained through iterative inversion, the internal defects of the wood structure can be accurately recognized and positioned, detection misjudgment caused by wave velocity deviation is avoided, and the reliability and practicability of wood structure defect detection are enhanced.

The invention relates to the technical field of ultrasonic tomography, and discloses a three-dimensional ultrasonic tomography sound velocity imaging method based on a multi-template fast marching method, which comprises the following steps: acquiring parameters of a three-dimensional ultrasonic tomography system and initial sound velocity distribution of biological tissues, and establishing a curved ray model based on an eikonal equation; discretizing the propagation time gradient in the eikonal equation by adopting second-order finite difference approximation, and covering 18 neighborhoods of the grid by adopting templates in four directions to carry out combined solution, so as to obtain ultrasonic propagation time distribution of the whole grid; and iteratively reconstructing a three-dimensional sound velocity distribution image through a maximum posterior probability estimation algorithm based on the ultrasonic propagation time distribution. According to the method, the propagation time gradient in the second-order finite difference approximation eikonal equation is adopted to reduce discretization errors, a plurality of direction templates are used, more accurate difference approximation is carried out on gradient operators, and the non-orthogonal propagation path of the ultrasonic waves in the three-dimensional space is completely captured.

The invention discloses an automatic driving scene reconstruction method and device, equipment and a storage medium, and belongs to the technical field of automobiles. The method specifically comprises the following steps: acquiring driving environment data sensed by a vehicle, wherein the driving environment data comprises first image data, first point cloud data and tracking data of a dynamic obstacle; performing sparse point clouding processing on the first image data to obtain second point cloud data; based on the first point cloud data and the second point cloud data, utilizing a preset two-stage alignment strategy to obtain static point cloud data; obtaining dynamic point cloud data based on the first point cloud data and the tracking data; performing semantic segmentation processing on the driving environment data to obtain fusion feature data based on a semantic segmentation processing result, the dynamic point cloud data and the static point cloud data; based on the fused feature data, utilizing a preset optimization strategy to obtain an optimization result, and rendering to generate an automatic driving scene image; and performing iterative reconstruction processing based on the scene image and the driving environment data to obtain a scene reconstruction result.