23 results about "Scale transformation" patented technology

The invention discloses a lithology generality joint feature classification model construction method, which relates to the technical field of intelligent geological prospecting, introduces a cross-scale feature alignment mechanism, and utilizes scale transformation factors to dynamically match the resolutions of macroscopic, mesoscopic and microscopic features, thereby avoiding feature distortion caused by direct fusion; for example, in a volcanic rock and sedimentary rock mixed area, rough texture of a remote sensing image originally conflicts with smooth response of a logging curve, but through alignment processing, the model can automatically balance credibility of different data sources, and misjudgment is reduced; inter-scale dependence modeling is further enhanced through introduction of the feature association graph, vertical sequence association of a thin interbed is captured through a graph structure, the boundary of a millimeter-level thin layer is made clear, and the problem of fuzziness caused by neglecting of interlayer interaction in an existing scheme is solved.

The invention provides a Gaussian neural field dynamic scene reconstruction system based on depth consistency constraint, and relates to the technical field of computer graphics, and the system comprises an estimation module which generates a target frame initial depth map; the calculation module reconstructs the point cloud and obtains a point cloud normal direction and a pixel normal direction; the optimization module is used for iteratively correcting the initial depth based on the two types of normal consistency to obtain an optimized depth map; the alignment module is used for determining a scale parameter through regression by taking the first target frame as a reference, and carrying out scale transformation on the depths of other frames to form a consistent depth sequence; the reconstruction module is used for constructing or training a Gaussian neural field based on the sequence and outputting a three-dimensional representation; in addition, the calculation module can contain multi-dimensional wavelets and sparse reconstruction and is used for multi-scale noise suppression and direction weighted fitting. Reference frame selection is based on frame-level quality, geometry and scale stability indexes; according to the system, the intra-frame geometric credibility and the cross-frame scale consistency are improved, ghosting and tearing are reduced, and the stability and integrity of dynamic scene reconstruction are enhanced.

The invention discloses a concrete structure damage variable-scale finite element simulation method based on two layers of grids, which comprises the following steps: step 1, respectively carrying out structure scale and material scale finite element grid subdivision on a concrete structure to obtain a structure-material two-layer grid covering the whole structure simulation area; 2, endowing material parameters to a structure scale unit and a material scale unit, and respectively establishing a structure scale finite element model and a material scale finite element model of the concrete structure; and 3, based on a simulation scale transformation criterion and a structure scale-material scale connection technology, dynamically updating the structure scale-material scale collaborative finite element model, and simulating a concrete structure damage evolution process. According to the method, the simulation scale of the damage area is converted based on the two layers of grids, so that the simulation precision of the concrete damage evolution process can be ensured, the calculation efficiency is relatively high, and the method has a wide application prospect in the refined analysis of the concrete structure damage evolution process.

The invention provides a lightweight semantic segmentation method and system for a remote sensing image of an urban scene, and relates to the technical field of semantic segmentation, and the method comprises the steps: carrying out the multi-scale transformation of the remote sensing image of the urban scene, carrying out the semantic feature extraction, obtaining a first semantic feature map under each reduced scale, adjusting the first semantic feature map, and obtaining a second semantic feature map under each reduced scale; using a second semantic feature map; performing forward, snake-direction and spiral scanning fusion operation on the second semantic feature map to obtain a third semantic feature map, and fusing the third semantic feature map with the third semantic feature map of the previous scale to obtain a fused semantic feature map; splicing the third semantic feature map and the up-sampling result of the fused semantic feature map of the previous reduced scale according to the channel dimension, and then performing two convolution operations and fusing; obtaining a fused feature image corresponding to a reduced scale; and taking an up-sampling result of the last scaled-down fusion feature image as a semantic segmentation result image.

Provided is a secure real-number multiplication method and apparatus based on scale transformation, which relates to the technical field of secure real-number multiplication. The secure real-number multiplication method includes: determining, by each participant, a private input value; performing, by each participant, scale transformation on the private input value to generate a private input matrix; with the private input matrix as input, computing, by each participant, a private output matrix by utilizing a Secure Two-Party Matrix Multiplication (S2PM) protocol based on a secure data disguising technology; calculating, by each participant, a sum of all elements in the private output matrix to obtain a private output value; and sending, by each participant, the private output value to a computation requester to obtain a secure real-number multiplication result.

Embodiments of the present application disclose a tongue feature recognition method and device, electronic equipment and a storage medium. The method comprises: acquiring a tongue image; performing multi-scale operation on the tongue image to determine at least two scale transformation images; inputting the at least two scale transformation images into a recognition model to output target feature information corresponding to the tongue image through the recognition model; and the recognition model is a cross-network model composed of a segmented convolutional neural network (Seg-CNN) structure and a point convolutional neural network (Point-CNN) structure. In this way, when analyzing the tongue image, the multi-scale operation is performed on the tongue image, and the network model composed of the Seg-CNN structure and the Point-CNN structure is used, so that the global feature information with points, lines and surfaces can be recognized, thereby the crack feature in the tongue image can be clearly recognized, and the recognition accuracy of the crack feature is improved.

The invention provides a steel bridge deck pavement performance multi-scale test evaluation method which comprises the following steps: acquiring test data of steel bridge deck pavement, and extracting a multi-scale performance parameter set from the test data; based on the multi-scale performance parameter set, establishing a scale conversion function for mapping local performance parameters to an overall structure state; constructing an initial digital model based on the scale transfer function and the multi-scale performance parameter set, and performing parameter reverse calibration on the initial digital model in combination with actually measured response data in the full-scale segment scale data to obtain a multi-scale performance digital model; and based on the multi-scale performance digital model, simulating the obtained service environment data of the target pavement structure to obtain performance evaluation data of the target pavement structure, the performance evaluation data including a predicted performance degradation value and a predicted remaining service life. By the adoption of the method, more reliable technical support can be provided for performance management and control of steel bridge deck pavement.

The invention relates to the technical field of image processing, and discloses a scale change-based real-time video jitter removal method, which comprises the following steps of: 1, acquiring a video frame at a previous moment as a pre-frame through single video shooting equipment, and acquiring a video frame at a current moment as a processing frame; step 2, pre-processing the obtained pre-frame and the processed frame; and step 3, extracting a preset number of feature points in the pre-processed pre-frame and the processed frame, matching the obtained feature points, removing mismatching points by using an RANSAC algorithm, and performing scale transformation and mapping on the matched feature points to the original size to obtain matching points of the pre-frame and the processed frame under the original size. The method comprises the following steps: preprocessing an acquired pre-frame and a processed frame, generating a low-resolution image through scale transformation downsampling, extracting feature points from the low-resolution image, removing mismatching points, and mapping the feature points to matching points with original sizes.

Provided are a secure two-party data comparison method and apparatus based on scale transformation. The method includes: transmitting, by a computation requesting party, a two-party data comparison request to two participant nodes; performing, by each participant node, scale transformation and linear scaling on private data locally after receiving the two-party data comparison request, to obtain an encrypted vector; determining, by each participant node, a real number locally using a secure two-party dot product protocol based on the local encrypted vector, and sharing the real number with the other participant node; determining, by each participant node, a comparison sign based on the obtained real number and transmitting the comparison sign to the computation requesting party; and determining, by the computation requesting party, a comparison result of the private data of the two participant nodes based on the comparison signs transmitted by the two participant nodes.

The application relates to the field of 3D vision, in particular to a point cloud shape analysis method based on a space geometry perception convolutional neural network. According to a K nearest neighbor algorithm, a point cloud is constructed as graph structure data, and a domain adaptive convolution kernel with different geometric shapes is adaptively generated according to features in each neighborhood. Subsequently, unit direction vectors, elevation angles and azimuth angles of neighborhood nodes are taken as prior geometric information, and convolution operation is performed on the generated convolution kernel to realize space geometry perception convolution operation. Subsequently, graph attention pooling is designed to coarsen the point cloud, realize multi-scale analysis and reduce the calculation cost. Finally, space geometry perception convolution and graph attention pooling are taken as basic units to construct two networks to realize point cloud classification and component segmentation tasks. The application can effectively classify and component segment target point clouds, and ensures the invariance of point cloud translation and scaling transformation, so that the model has stronger robustness.

The application discloses a kind of tax-related legal text-oriented named entity recognition dependent enhancement method, comprising: tax named entity recognition is regarded as span classification task, a large number of spans are enumerated from input text by sliding window, and the deep representation of each span is generated by feature splicing method;Introduce a contrastive learning loss, and the contrast relationship is mined from highly overlapping span;Scale transformation mechanism is used to realize span interaction, and the geometric information of each candidate span is embedded in native span representation, to encode the interaction dependency between spans.The application converts tax named entity recognition into span classification task, and fully mines the interaction dependency between entities, realizes strong inference relationship, and introduces contrastive learning to improve the discrimination degree between different types of highly overlapping entities, so that the named entity in tax legal text can be more accurately and reasonably recognized, laying a foundation for downstream tasks such as tax incentives.

The invention discloses a three-dimensional reconstruction method and system based on multi-view image fusion. The method comprises the following steps: carrying out adaptive segmentation on an obtained long image line by line to generate a segmentation mask; executing cylindrical surface expansion mapping on the target surface according to the mask segmentation result to obtain corrected plane textures; seamless fusion processing is carried out on the plane textures under the multiple visual angles to generate 360-degree panoramic textures; based on the pixel width W of the panoramic texture, performing scale transformation and displacement processing on the coordinates of the texture U; and mapping the panoramic texture subjected to scale transformation and displacement processing on the texture U coordinates to a three-dimensional cylindrical model to generate a high-fidelity three-dimensional reconstruction model of the target object. According to the method, the problems of insufficient image segmentation precision, incomplete cylinder perspective distortion correction, visual flaws of multi-view texture splicing and joints in three-dimensional model rendering in the three-dimensional reconstruction process of a slender cylindrical object (such as a steel wire rope) can be effectively solved.

The application provides a range scale conversion algorithm, and belongs to the technical field of airborne SAR polar format algorithm (PFA) real-time imaging, and specifically comprises the following steps: embedding compensation processing of a fast time offset Delta tau corresponding to each pulse into a matched filter to complete scene center point motion compensation and pulse compression processing of each pulse; and then performing range intercept processing on the pulse compressed data to complete imaging processing of a region of interest near an imaging center, so that the problem of image winding caused by range intercept in the original algorithm can be solved, and the azimuth interpolation processing time and the storage capacity requirement of an imaging system are greatly reduced.

The invention discloses a multi-scale transformation seismic event detection method based on a seabed application scene, and relates to the technical field of seismic event detection. According to the seismic event detection method based on the multi-scale comprehensive transformation of the seabed application scene, a plurality of channel original signals are collected through a seabed seismograph, and a fusion feature vector is constructed through multi-scale time-frequency transformation; performing local event preliminary screening, generating an event packet, and reporting the event packet to the buoy node; in the buoy nodes, event packets uploaded by all the ocean bottom seismometers in the jurisdiction range of the buoy nodes are received, and a cluster report is generated and transmitted to the shore-based processing center after the weighted comprehensive confidence coefficient is analyzed; in a shore-based processing center, cluster event reports uploaded by all buoy nodes within the range where the shore-based processing center is located are received, and the global existence probability of the same event is analyzed. And determining the same event higher than a preset global existence probability threshold as a real seismic event.

The invention relates to the technical field of large language models, in particular to a method for detecting a large language model LoRA fine tuning origin. Comprising the steps of generating an adaptability vocabulary, recording intermediate features of a to-be-verified model, selecting a base candidate model, obtaining output features of the base candidate model, calculating approximate intermediate features of the base model, extracting LoRA rank information through singular value decomposition, determining minimum rank information and judging a fine tuning origin. According to the method and the system for detecting the LoRA fine-tuning origin of the large language model, the fine-tuning origin of the model can still be accurately detected in the face of confusion technologies such as parameter replacement and zoom transformation, the defect of confusion resistance in the prior art is effectively overcome, the LoRA rank information used in the fine-tuning process can be accurately extracted, a detailed basis is provided for model verification, and the method and the system are suitable for popularization and application. The method facilitates further analysis of fine adjustment details of the model, is suitable for large language models of various architectures and scales, is not limited by the size of the model and specific fine adjustment parameters, and has wide applicability.

The invention discloses a method for simplifying a building polygon in map synthesis based on a large language model normal form. The method comprises the following steps: acquiring a coordinate data sequence of a vector building polygon to be simplified; the coordinate data of the vector building polygon to be simplified are input into a simplification model based on a large language model normal form, a simplified polygon is obtained, simplification of the building polygon in scale transformation from a large scale to a small scale is achieved, and the simplification model constructs a vocabulary through a gridding mechanism; discretizing an original coordinate sequence in the vector building polygon to be simplified into a Token sequence; a mask self-attention mechanism of a Transform of a decoder structure is adopted to learn context dependence of a polygon point sequence, and feature embedding of each point is formed; and finally, point-by-point generation of the simplified polygon is realized through a full-connection neural network.

This invention discloses a behavior recognition method based on spatiotemporal scale transformation, comprising: detecting a target using a target detector to obtain corresponding target bounding box regions; performing spatial multi-scale transformation on each target region to obtain multi-scale target regions; fusing features of the multi-scale target regions to obtain fused features; and classifying and recognizing behaviors based on the fused features. This invention combines target detection with behavior recognition, enabling the behavior recognition model to effectively focus on the regions where behaviors actually occur. Addressing the problem of inconsistent target spatial scales, this invention utilizes upsampling and downsampling to achieve scale uniformity, better ensuring the scale consistency of targets. To address the temporal differences between different samples, this method proposes a multi-frame-rate sampling operation to fuse features from multiple time scales, enabling effective feature extraction for behaviors of different durations.

The invention discloses an infrared and visible light image fusion method fusing adaptive decomposition and multi-scale transformation, and relates to the technical field of multi-modal image fusion. In order to solve the problems of detail loss, noise interference, structural distortion and the like in infrared and visible light image fusion, the method comprises the steps of firstly performing normalization and registration preprocessing on an input image, then extracting low-frequency and high-frequency features by adopting adaptive Fourier decomposition, and performing sparse representation and orthogonal matching pursuit fusion on a low-frequency part to obtain a low-frequency part and a high-frequency part; and the high-frequency part guides dynamic weighted fusion according to local energy and information entropy, and finally reconstruction is performed and cross-scale consistency verification is introduced to improve fusion robustness. The method can be widely applied to fusion of infrared and visible light images, and the quality of the fused image is improved.

The invention provides a target original echo signal recovery method, which uses an interpolation function based on fast Fourier transform to perform up-sampling, then combines a frequency spectrum position index after scale transform to complete inverse stolt mapping processing based on scale transform, and finally achieves the purpose of high-precision recovery of target original echo signals. According to the target original echo signal recovered by the method, the range walk of the moving target can be removed through motion compensation, and the azimuth focusing degree of the moving target is improved. Compared with sinc interpolation, the inverse stolt mapping processing based on scale transformation is completed by using the interpolation function based on fast Fourier transformation and the frequency spectrum position index after scale transformation, and the calculation efficiency is higher.

The application discloses a scale transformation-based secure two-party numerical comparison method and device, relates to the field of data security, and comprises the following steps: a computing request direction two-party node sends a two-party numerical comparison request; after receiving the two-party numerical comparison request, the two-party node locally performs scale transformation and linear scaling processing on private data in sequence to obtain an encrypted vector; the two-party node determines a real number locally according to the local encrypted vector by using a secure two-party scalar product protocol, and shares the real number with other two-party nodes; the two-party node respectively determines a numerical comparison symbol according to the obtained real number and sends the numerical comparison symbol to the computing request party; and the computing request party determines a comparison result of the private data of the two-party nodes according to the numerical comparison symbols sent by the two-party nodes. The application improves the security of private data in the two-party numerical comparison process.

The invention provides a multi-scale transformation point cloud registration method and device and electronic equipment, and the method comprises the steps: carrying out the voxel grid down-sampling processing of a source point cloud and a target point cloud through sequentially employing each voxel size in a voxel size sequence, and carrying out the corresponding scale transformation based on the source point cloud and the target point cloud after each voxel grid down-sampling processing, and in each round of scale transformation, mapping the source point cloud to a coordinate system where the target point cloud is located based on the current transformation matrix, and executing multiple iterations to carry out transformation matrix estimation until a preset stop condition is met, and obtaining a transformation matrix of the current round. And after the last round of scale transformation is completed, the transformation matrixes obtained by each round of scale transformation are compounded in sequence to obtain a final transformation matrix, and the source point cloud is registered to the target point cloud based on the final transformation matrix. According to the scheme, a multi-scale registration mechanism is introduced, the global convergence and stability of the algorithm can be remarkably enhanced through a coarse-to-fine layer-by-layer alignment strategy, and meanwhile, a local optimal trap is inhibited.

The invention discloses a parameter adaptive noise suppression method based on multi-scale feature reconstruction. The method comprises the following steps: 1, carrying out mathematical modeling on an image under noise interference; 2, performing wavelet transformation on the image, and extracting feature information in the image; 3, constructing an edge evaluation index for the high-frequency sub-band of the image; 4, processing the low-frequency wavelet coefficient and the high-frequency wavelet coefficient of each layer; and 5, carrying out wavelet inverse transformation processing to obtain a reconstructed image after noise removal. According to the method, the image features are extracted through multi-scale transformation, the features of different scales can be subjected to differential processing according to the features of the features, the algorithm has adaptability, filtering processing of different intensities can be carried out according to the proportion of detail information contained in the high-frequency sub-band in the same scale, and the filtering accuracy is improved. The adaptive mechanism effectively improves the accuracy and efficiency of parameter adjustment, better retains the texture details of the image, and has very high social significance and economic value in the field of image denoising.

A multi-scale transformation and generalized spectral entropy driven multi-type energy storage new energy stabilizing method comprises the following steps: step 1, respectively carrying out S transformation, wavelet packet transformation and self-adaptive improved multiple synchronous extrusion transformation on a collected new energy power sequence signal to obtain a corresponding time-frequency graph; 2, normalizing the three types of time-frequency diagrams respectively, and building a weighted fusion model according to a normalized structure; 3, taking the generalized spectral entropy as a target function, constructing a weight optimization model taking the minimum spectral entropy as a criterion, obtaining an optimal fusion coefficient, and optimizing the weight fusion model; and 4, establishing a frequency interval division and component level reconstruction mechanism for the optimized time-frequency graph of the weighted fusion model. The method comprises the following steps: performing multi-scale decomposition on new energy power to obtain fluctuation components with different frequency characteristics; matching adaptive stored energy for the components according to response characteristics of the stored energy; and finally, control parameters are optimized through generalized spectral entropy, multi-energy-storage collaborative stabilization is realized, and adaptability and precision are improved.