289results about How to "Improve reconstruction accuracy" patented technology

The invention relates to the technical field of image processing, and particularly discloses a remote sensing image super-resolution reconstruction method and system based on a prior diffusion model, and the method comprises the steps: carrying out the shallow feature information extraction of a low-resolution image, and obtaining a shallow feature map; the method comprises the following steps: performing multi-scale down-sampling and convolution fusion processing on a shallow feature map and a high-resolution image, and performing high-frequency information extraction and adaptive high-frequency enhancement processing on the processed feature map to obtain condition information; according to the method, deep mining of high-frequency information is carried out on a low-resolution image input as condition information, so that the high-frequency information in the low-resolution image gradually approaches a high-resolution image, and the reconstruction precision is improved; the noise prediction network model guides step-by-step noise removal in the back diffusion process, and the detail reduction capability and precision of natural disaster remote sensing image super-resolution reconstruction are improved.

The invention belongs to the field of computer graphics, and discloses a fast parallel multi-scale smooth symbol distance curved surface reconstruction method and system, and the method comprises the steps: carrying out the local fitting of point cloud data through employing a moving least square method, and calculating the Gaussian curvature of a point cloud; constructing a curvature adaptive octree based on Gaussian curvature, wherein the octree is used for dynamically adjusting local resolution and capturing geometric details to improve curved surface reconstruction precision; global fitting is carried out through an implicit function, and a zero contour surface is obtained through an octree contour surface extraction algorithm; and multiple threads are introduced in the process of iteratively solving the linear system to carry out parallel computing. The adaptive octree based on Gaussian curvature can effectively capture complex geometric details, and the algorithm realizes high-precision curved surface reconstruction under different scales. In addition, the local and overall calculation efficiency is remarkably improved through parallel calculation, and the high efficiency of the algorithm in large-scale data processing is ensured. The method provided by the invention provides an efficient and accurate solution for complex curved surface reconstruction.

The invention provides a bone image superposition presentation method and system based on an augmented reality technology, and relates to the technical field of intelligent medical systems.The method comprises the steps that fracture image data for a fracture area of a patient are acquired, and the fracture image data comprise a CT image, an X-ray image and a light field image; analyzing a light model corresponding to the light field image; the light model provides propagation information of light in a fracture area space of a patient; determining multi-modal fusion features corresponding to the fracture image data based on a light model and a feature fusion network; the feature fusion network adopts a convolutional neural network; reconstructing a three-dimensional model of the fracture part based on the multi-modal fusion features; and aligning and calibrating the reconstructed three-dimensional model of the fracture part and the fracture area of the patient in the actual operation scene. Therefore, the augmented reality technology, the light model and the feature fusion network are comprehensively applied, the three-dimensional model of the fracture part is accurately overlaid and presented in real time in a real operation scene space, and the accuracy and efficiency of the operation can be remarkably improved.

The invention discloses a power grid toughness evaluation method and system, and the method comprises the steps: inputting the collected monitoring index data and environment index data of a target regional power grid into a pre-trained power grid toughness evaluation model for evaluation and recognition, so as to obtain a toughness evaluation result; the monitoring index data comprises voltage data, current data, harmonic data and power data, and the environment index data comprises temperature and humidity data, line loss data and frequency data; wherein the construction process of the power grid toughness evaluation model comprises the step of respectively training a data expansion process, a feature extraction model, a feature dimension reduction model and a classifier model in the power grid toughness evaluation model, so as to obtain the power grid toughness evaluation model. The evaluation accuracy of the evaluation model is improved by optimizing the training process of the model.

The invention provides an image processing method, device and equipment for scene reconstruction and rendering. The method comprises the following steps: initializing sparse point clouds corresponding to each scene image to be reconstructed to obtain a plurality of initial Gaussian surface elements; optimizing each initial Gaussian surface element based on an inverse depth map, a rendering scene image and a normal vector map obtained by rendering the initial Gaussian surface elements to obtain a plurality of first target Gaussian surface elements; based on the importance of the first target Gaussian surface elements, determining a second target Gaussian surface element, the importance being determined based on a plurality of sub-models and a target scene image to be reconstructed matched with each sub-model, the plurality of sub-models being obtained by performing mesh generation on the plurality of first target Gaussian surface elements, and the plurality of sub-models being obtained by performing mesh generation on the plurality of first target Gaussian surface elements; the target scene image to be reconstructed matched with each sub-model is determined based on the pose of the scene image to be reconstructed and the rendering result of the sub-model; and determining a third target Gaussian surface element for rendering the reconstructed scene image based on the spatial range of the grid.

The invention discloses a method and system for inverting an ocean three-dimensional temperature structure based on sea surface data, and relates to the technical field of remote sensing, and the method comprises the steps: obtaining the reanalysis data of a target sea area, and carrying out the data preprocessing; according to the processed reanalysis data, training the ocean three-dimensional temperature reconstruction model to obtain a trained ocean three-dimensional temperature reconstruction model; the ocean three-dimensional temperature reconstruction model is a reconstruction model of an ocean three-dimensional temperature field constructed by selecting a U-net network; in the training process of the ocean three-dimensional temperature reconstruction model, a loss function sensitivity test and a temperature field inversion model sensitivity test based on a U-net network are adopted to optimize the performance of the ocean three-dimensional temperature reconstruction model; and according to the real-time sea surface data of the target sea area, constructing an ocean three-dimensional temperature structure based on the trained ocean three-dimensional temperature reconstruction model. According to the invention, the reconstruction precision of the ocean three-dimensional temperature field can be improved, and rapid and real-time temperature field reconstruction can be realized.

The invention discloses a rotor blade dynamic field rapid reconstruction method based on a deep neural network model, and the method comprises the steps: firstly collecting a BTT signal containing blade vibration information, then designing a deep neural network model, and training the deep neural network model through a training data set; processing the actually measured BTT signal by using the trained deep neural network model, and reconstructing a blade vibration displacement signal; performing spectral analysis on the reconstructed blade vibration displacement signal, and identifying vibration frequency, amplitude and phase parameters; then establishing a finite element model of the blade, and determining the inherent frequency and modal shape of the blade through modal analysis; and finally, quickly calculating a displacement field, a strain field and a stress field of the blade in a vibration state based on a modal superposition theory by utilizing the identified vibration parameters and modal analysis results. According to the invention, the vibration displacement and stress condition of the blade can be known in real time, so that real-time decision is supported, and the safety, reliability and durability of a rotating machine are improved.

The invention discloses a time-frequency domain cooperative industrial Internet of Things anomaly detection method under a full MLP lightweight architecture, and the method only employs four parallel two-layer MLP networks to construct a lightweight full MLP architecture with high timeliness and low resource consumption, and guarantees that the lightweight full MLP architecture can be flexibly applied in an industrial scene with limited resources. According to the architecture, a double-branch reconstruction learning process is constructed from two angles of'local to global 'and'global to local'; in order to further improve the accuracy, the reconstruction learning process of each branch utilizes two two-layer MLP networks to carry out reconstruction learning in a time domain and a frequency domain respectively, and the time domain and the frequency domain are aligned by utilizing reconstruction consistency, so that the feature capture capability of the full MLP architecture is improved; and finally, designing an anomaly scoring scheme based on a time-frequency reconstruction error, fusing the time-frequency domain reconstruction error obtained in double-branch reconstruction learning by using different weights, thereby generating a final anomaly score for each timestamp, and further judging whether the timestamp is abnormal or not.

The invention provides an underwater multi-view three-dimensional reconstruction method. The underwater multi-view three-dimensional reconstruction method mainly comprises the following steps: S1, acquiring a high-quality multi-view underwater image through a physical perception image enhancement technology PUIE; s2, initializing a neural symbol distance function SDF, and implicitly representing the three-dimensional shape of an object by a neural network; s3, generating a two-dimensional foreground mask by using few-sample multi-view target segmentation, and obtaining three-dimensional geometric information in combination with monocular depth estimation and normal vector prediction to form mixed geometric prior; and S4, in combination with an image enhancement result and mixed geometric priori, through a joint loss function, training a neural network optimization SDF, and completing accurate three-dimensional reconstruction. According to the underwater three-dimensional reconstruction method, a more efficient and more accurate underwater three-dimensional reconstruction solution is provided by introducing mixed geometric prior and optimizing the reconstruction process of the neural symbol distance function SDF.

The invention discloses a three-dimensional reconstruction method and system based on a line shift coding pattern, and the method comprises the steps: designing an original fringe pattern in a line shift manner to obtain a plurality of coding patterns, and carrying out the projection and collection of a to-be-measured object through the plurality of coding patterns and a preset Gray code pattern, respectively obtaining a plurality of fringe projection drawings and a plurality of Gray code projection drawings; synthesizing M phase shift fringe patterns according to the collected multiple fringe projection patterns; performing phase calculation on the M phase shift fringe diagrams to obtain a folded phase diagram; and combining the folded phase diagram with the plurality of Gray code projection drawings for phase unwrapping to obtain an unwrapped phase diagram, and reconstructing the to-be-measured object by using a three-dimensional reconstruction principle. According to the method, fringe synthesis is firstly carried out on the plurality of coding patterns, and then phase calculation is carried out on the M phase shift fringe patterns, so that three-dimensional reconstruction is carried out on the to-be-measured object by using the phase, relatively high reconstruction precision is achieved, the robustness is relatively high, and the method has a relatively good application effect in a high dynamic range scene.

The invention provides a Mama-based cross-view binocular image super-resolution reconstruction method and system, and the method comprises the steps: carrying out the modeling of a binocular image long-distance dependence relation through a CSOMM deep feature extraction module, and extracting the contour and texture information of a left view feature and a right view feature; a robust corresponding relation is established between a left view and a right view through a cross-view selection scanning module by adopting a cross multiplication mechanism, so that complementary information between binocular images is fully utilized, and the reconstruction precision and stability of the network are further improved; and the pixel shuffling layer is used for performing up-sampling reconstruction on the output of the cross-view feature interaction module to obtain a reconstructed binocular image. According to the scheme, the corresponding relation between binocular images can be fully utilized, the image texture and structure can be finely processed on the multi-channel and multi-view level, and more accurate and high-quality image reconstruction is achieved.

The invention discloses a three-dimensional reconstruction method based on linear structure light spot set monomer kinematics calibration, and the method comprises the steps: enabling an area-array camera and a linear structure light emitter to be rigidly combined, and enabling the area-array camera and the linear structure light emitter to be installed on a motion platform; calibrating structural parameters of a motion platform of the measuring device by using the radius standard value of the standard ball and the linear structured light scanning data; calibrating the spatial position relation of the line scanning point set by taking the calibrated center position of the standard ball and the standard radius of the standard ball as constraints; controlling the five-axis motion platform to move and acquiring scanning data of the measured piece under different poses; and the scanning data and the real-time point cloud calibration matrix are utilized to complete the multi-pose scanning high-quality three-dimensional model reconstruction of the measured piece. The system comprises a device fixing module, a calibration module, a point cloud calibration module, a scanning module and a point cloud reconstruction module. According to the invention, the reconstruction precision of the line structured light three-dimensional point cloud model can be improved. The method can be widely applied to the field of three-dimensional reconstruction.

The invention provides an MRI (Magnetic Resonance Imaging) reconstruction method of a subspace diffusion model based on orthogonal decomposition. The MRI reconstruction method comprises the following steps: forming an open source brain data set; a subspace diffusion model based on orthogonal decomposition is constructed, and k-space data is decomposed into subspaces for diffusion, so that data distribution is better captured, and robustness is kept in a noise environment; designing an iterative solution algorithm for extracting prior information in the model; and applying an iterative solution algorithm to the model to test the test data set, and outputting a final restored image. According to the method, the learning of effective information in complex distribution is promoted, the inherent high-dimensional extrapolation challenge is solved, and the calculation cost related to a diffusion model is reduced. Comprehensive experiments on different data sets clearly show that the method is superior to other methods in the aspects of reconstruction speed and quality.

The invention relates to the technical field of underwater acoustic communication, in particular to an underwater acoustic communication receiving method based on superimposed interference signals. According to prior information of interference signals, a sparse channel time domain signal reconstruction scheme based on a fast soft threshold iterative algorithm (FISTA) is provided, and the scheme has higher reconstruction accuracy for sonar interference signals; aiming at the influence of a residual sonar interference signal, a multipath effect and environmental noise, a VTRM equalization method based on FISTA sparse estimation and a non-parametric Viterbi decoding algorithm based on a Gaussian kernel are provided, so that the influence caused by the multipath effect and the environmental noise can be well solved; and the performance of underwater acoustic communication and the signal receiving precision are effectively improved.

The invention discloses a hierarchical object modeling and rapid reconstruction method based on NeRF, and the method comprises the following steps: image preprocessing: initially obtaining an image video frame through a camera, carrying out the related processing of an input image, including semantic segmentation, depth estimation, normal estimation and internal and external parameter calibration, and generating a corresponding semantic graph, a depth graph, a normal graph and camera parameters; space partitioning: partitioning the scene according to the semantic graph information and defining a bounding box; adaptive sampling: performing adaptive sampling by combining the depth map, the normal map and the camera parameters, and determining a sampling point set; and performing hierarchical vectorization SDF reconstruction, performing hierarchical vectorization SDF reconstruction by using the sampling points to obtain hierarchical SDF representation describing the shape of the object, converting the hierarchical SDF into a triangular mesh model, and completing three-dimensional object modeling and rapid reconstruction. The invention provides a hierarchical object modeling and rapid reconstruction method based on NeRF, objects in a scene are rapidly reconstructed, and downstream editing tasks, interaction and other applications are supported.

The invention relates to the technical field of motor control technologies, and particularly provides a permanent magnet synchronous motor back electromotive force reconstruction and position speed extraction method, which comprises the following steps of: establishing a mathematical dynamic model of a permanent magnet synchronous motor under a static coordinate system, and designing an improved super-spiral observer according to the model, the reconstruction precision and the convergence speed of the back electromotive force are enhanced; and standardizing the reconstructed back electromotive force, and extracting the position and speed of the permanent magnet synchronous motor rotor through an integral compensation phase-locked loop. According to the invention, by improving the existing super-spiral observer and the phase-locked loop, the convergence speed and the position estimation precision of the system are obviously improved.

The invention discloses a satellite-borne frequency polarization reconfigurable liquid metal broadband oscillator antenna, and the antenna comprises an antenna bottom plate which comprises a lower-layer bottom plate and an upper-layer bottom plate; the radiation arms are in an L shape, a pipeline loop is arranged in each radiation arm, two ports of each pipeline loop are located on the end face of the short section of the corresponding radiation arm, the pipeline loops are filled with liquid metal and insulating mineral oil, and the long section of each radiation arm is parallel to the upper-layer bottom plate; shorter sections of the radiation arms penetrate through the through holes of the upper-layer bottom plate to be mounted on the lower-layer bottom plate, and the four radiation arms form a cross layout form with a space reserved in the middle; the feed structure is mounted on the lower-layer bottom plate and located in the middle of the four radiation arms; and the four liquid metal driving control structures are mounted on the lower-layer bottom plate and are respectively used for controlling the lengths of the liquid metal in the pipeline loops of the four radiation arms. The ultra-wideband frequency reconstruction of the antenna can be realized, the polarization reconstruction of the antenna is realized, the reconstruction speed and the reconstruction precision are high, the stability is good, and the repeatability is high.

The present invention discloses a method and system for replicating digital human images based on NeRF, and relates to the technical field of digital human image replicating. The method comprises: collecting digital human images to obtain training data sets; expanding and generating training samples; reconstructing a model using the expanded digital human image data training data; extracting features from the results of digital human image replicating output by the autoencoder, and inputting the feature vector after feature extraction into the classifier model to perform digital human image data screening. The present invention improves the details and authenticity of the generated samples, makes the expanded data closer to the real collected images in terms of fidelity, enhances the adaptability and stability when screening digital human image data, makes the screening model more adaptable when facing diversified replica data, improves the classification effect, and finally ensures the high quality and consistency of the replica data.

The invention provides a hyperspectral image super-resolution reconstruction method, which is characterized in that a super-resolution reconstruction model comprises a tensor construction module used for generating a high-resolution multispectral image tensor and a low-resolution hyperspectral image tensor; the gating cross-keeping sharing module is used for obtaining a first output corresponding to the low-resolution hyperspectral image tensor and a second output corresponding to the high-resolution multispectral image tensor according to the low-resolution hyperspectral image tensor and the high-resolution multispectral image tensor; the hyperspectral channel attention module is used for performing feature extraction on the first output to obtain a channel attention feature map; the multispectral spatial attention module is used for performing feature extraction on the second output to obtain a spatial attention feature map; and the fusion module is used for performing multi-level feature fusion on the channel attention feature map and the space attention feature map to obtain a high-resolution hyperspectral image. In a word, the method can generate a high-precision high-resolution hyperspectral image.

A method for automatically generating a three-dimensional model of power transmission line construction equipment comprises the following steps: performing target detection on a to-be-detected image based on an SSD network model and generating candidate boxes, and screening the candidate boxes by using a non-maximum suppression method to obtain a to-be-reconstructed image; the method comprises the following steps of: performing feature point extraction and matching on any two to-be-reconstructed images by using an SURF algorithm and an AKAZE algorithm to obtain a first feature point matching set and a second feature point matching set, and finally performing three-dimensional reconstruction on the power transmission line construction equipment based on the first feature point matching set and the second feature point matching set to generate a three-dimensional model of the power transmission line construction equipment. According to the method, on the basis of extracting the main feature points by using the SURF algorithm, the edge feature points are extracted by using the AKAZE algorithm, so that the extracted feature points are more comprehensive, and the subsequent three-dimensional model reconstruction precision is further improved.

The invention provides a hyperspectral image reconstruction method based on space-spectral characteristic fusion. The method comprises the following implementation steps: acquiring a training sample set and a test sample set; constructing a reconstruction network model based on space-spectral characteristic fusion; performing iterative training on the reconstructed network model; and obtaining a reconstruction result of the hyperspectral image. According to the invention, the spatial-spectral characteristic guiding network in the encoder carries out spatial-spectral characteristic extraction on input characteristics, the spatial-spectral characteristic guiding network in the bottleneck layer carries out spatial-spectral characteristic fusion, the spatial-spectral characteristic guiding network in the decoder carries out spatial-spectral characteristic detail recovery, spatial structure information and spectral distribution information in the input characteristics are fully extracted, and the spatial-spectral characteristic guiding network in the decoder carries out spatial-spectral characteristic fusion. The spatial features and the spectral features cooperatively participate in the reconstruction process, and cooperative recovery of the spatial information and the spectral information of the hyperspectral image is realized, so that the reconstruction precision of the hyperspectral image is effectively improved.

The invention belongs to the field of artificial intelligence and financial science and technology, and relates to a human face three-dimensional reconstruction method and device based on artificial intelligence, computer equipment and a storage medium, and the method comprises the steps: carrying out the region-of-interest extraction of two-dimensional human face image data, obtaining a human face image, carrying out the key point detection of the human face image, and obtaining two-dimensional key points; performing face segmentation on the face image to obtain a face mask image; processing the face image based on the initial reconstruction model to obtain a three-dimensional face model; generating a first loss based on the three-dimensional face model and the face image; generating a second loss based on the three-dimensional face model, the two-dimensional key points and the face mask image; generating a comprehensive loss based on the first loss and the second loss; optimizing the initial reconstruction model based on the comprehensive loss to obtain a target reconstruction model; and performing three-dimensional reconstruction processing on the face image based on the target reconstruction model to obtain a target three-dimensional face model. According to the invention, the precision of three-dimensional face reconstruction is improved based on the use of the target reconstruction model.

The invention belongs to the technical field of medical image processing, and provides a CBCT artifact correction system and method based on a multi-stage reconstruction network. The system comprises an image preprocessing module, a model training module and an image generation module, wherein the image preprocessing module is used for reconstructing projection data acquired by CBCT scanning to obtain a reference CBCT and a sparse angle CBCT; the model training module is used for training a multi-stage mixed attention reconstruction network based on the sparse angle CBCT and the reference CBCT to obtain a sparse angle CBCT artifact correction model; and the image generation module is used for inputting the actual sparse angle CBCT into the sparse angle CBCT artifact correction model to generate a corrected CBCT. Through multi-stage fusion of the image domain and the projection domain, common stripe artifacts and noise in sparse angle reconstruction are effectively reduced, and the definition and clinical availability of CBCT are improved.

The invention relates to an asteroid gravitational field reconstruction method based on an embedded mathematical knowledge neural density field, and the method comprises the steps: completing the sampling of data points based on an asteroid mass point group model, and constructing a function solver from a spatial position to density; constructing a spatial sampling point function to obtain spatial densities of spatial points at different positions; aiming at the space points, utilizing an asteroid visual three-dimensional model to obtain star shell information, and screening the space points as prior information inside and outside a star shell; screening results of the density function solver according to prior information; further calculating a Laplace equation of the data points by using a partial differential equation solver, and calculating a gravitational acceleration equation of external space points of the star by using numerical integration; constructing a total loss function; error back propagation is carried out, and network parameters are optimized; recalculating the internal space point density of the star to obtain the internal density distribution of the asteroid; and further calculating the value of the gravitational acceleration of each position in the space to obtain asteroid external gravitational field distribution.

The invention provides a diffusion-driven channel adaptive point cloud semantic communication method, which belongs to the technical field of wireless communication, and comprises the following steps: obtaining a training point cloud data set, constructing a point cloud feature extraction network based on a hypergraph convolutional neural network as a semantic encoder, and constructing a channel adaptive enhancement module as a channel decoder, a channel adaptive recovery module is constructed at a receiving end as a channel decoder, a diffusion reconstruction network is constructed as a semantic decoder, end-to-end joint training is performed on the point cloud feature extraction network, the channel adaptive enhancement module, the channel adaptive recovery module and the diffusion reconstruction network, the diffusion reconstruction network predicts original point cloud distribution, and the point cloud feature extraction network and the channel adaptive enhancement module are subjected to end-to-end joint training. And a loss function is constructed based on the chamfering distance between the predicted point cloud distribution and the original point cloud. In the communication process, the reconstructed semantic features are input into the diffusion reconstruction network to reconstruct an original point cloud structure. The high-order semantic features of the point cloud can be effectively extracted so as to improve the adaptive capacity of the method to the incomplete point cloud.

The invention discloses an earth surface exposed geologic body reality sense three-dimensional reconstruction method based on a neural radiation field. The method comprises the steps that an earth surface geologic body image data set is acquired; performing feature matching on the image data set by using a feature matching strategy based on a nearest neighbor algorithm and a LightGlue neural network to generate feature point matching information and a feature description file; sparse three-dimensional point cloud data and camera pose information are obtained based on incremental SfM; and obtaining depth information of an image data set based on sparse three-dimensional point cloud data and camera pose information, and establishing a geologic body realistic three-dimensional reconstruction model by using a neural radiation field optimization method fusing the depth information and Gaussian position coding. According to the method, the feature matching precision and the camera pose calculation accuracy are improved, the texture detail expression ability of a geological structure can be improved, the reconstruction quality of a surface geologic body model is enhanced, and geological information support can be provided for the fields of geological research and engineering application.

The invention provides a three-dimensional multi-mode nuclear magnetic resonance image reconstruction method, which comprises the following steps of: 1, processing a data set, selecting an auxiliary mode and a target mode, further performing down-sampling processing on the target mode and reserving a true value; step 2, establishing a multi-modal encoder as a feature extraction module for extracting and interacting effective features of the multi-modal data; 3, establishing a decoding module based on multi-scale feature fusion, wherein the decoding module is used for decoding cross-domain links of effective features and layer-by-layer decoding of target modal features in the encoding process; and step 4, network training based on supervised learning is carried out to obtain a trained 3DMRI reconstruction model so as to meet the demand of accelerating nuclear magnetic resonance imaging. By means of the method, various modal features and depth information can be better extracted and fused, and the precision of a model reconstruction image is greatly improved.

The invention belongs to the communication technology, and particularly relates to a GNSS receiver array anti-interference method combining multivariate variational mode decomposition and dictionary learning, which comprises the following steps: obtaining each intrinsic mode component after an array receiving signal is subjected to multivariate variational mode decomposition, and reconstructing a noise-free signal after effective mode selection; and carrying out dictionary learning by using a noise-free signal, reconstructing an interference signal according to a trained dictionary, and subtracting the reconstructed interference signal from an array receiving signal to realize suppression of the interference signal. The method can effectively relieve the influence of noise components on signals, and guarantees the interference recognition precision of a subsequent algorithm. And the adopted dictionary learning algorithm can effectively identify interference signals of known types.

The invention relates to a training method and device of a particle flow field reconstruction model and a particle flow field reconstruction method and device. The initial particle flow field reconstruction model comprises a pulse coding module, a cost volume fusion coding module and a particle flow field reconstruction module. The method comprises the following steps: acquiring sample pulse image data; performing feature extraction processing on the sample pulse image data collected in the different time windows to obtain a plurality of pulse feature maps corresponding to the different time windows, determining a local cost volume based on the corresponding pulse feature maps in the different time windows, and determining a total cost volume based on the pulse feature maps in all the time windows; fusing the local cost volume and the total cost volume to obtain a multi-time-step cost volume memory; and performing reconstruction processing on the multi-time-step volume memory to obtain a reconstructed particle flow field, and training the initial particle flow field reconstruction model to obtain a particle flow field reconstruction model. By adopting the method, the flow field reconstruction precision can be improved.

The invention discloses an RTU data reconstruction method and device based on a generative adversarial network, and a medium. The method comprises the following steps: obtaining power grid data from a power grid monitoring point; encoding the power grid data into a channel and an image matrix of the binary image according to the parameter type to obtain an RTU electrical image; performing frequency raising reconstruction processing on the RTU electrical image by optimizing the data reconstruction model to obtain reconstructed RTU data; wherein the optimized data reconstruction model is established according to the generator model and the discriminator model. According to the RTU data reconstruction method and device based on the generative adversarial network and the medium, data compression is achieved by encoding power grid data into a binary image, meanwhile, key information of the data is reserved, high-frequency details in the power grid data can be remarkably improved by optimizing frequency-raising reconstruction processing of a data reconstruction model, and the data reconstruction efficiency is improved. The problem that electrical reconstruction data lacks high-frequency details can be solved.