31 results about "Dual tree" patented technology

An electronic device performs a method of decoding video data. The method comprises: receiving, from the bitstream, a plurality of syntax elements associated with an encoding unit, wherein the plurality of syntax elements indicates the encoding tree type of the encoding unit and whether local dual-tree mode is enabled for the encoding unit; and, based on the determination that the encoding tree type of the encoding unit is single-tree and that local dual-tree mode is enabled for the encoding unit; disabling palette mode for the encoding unit when the encoding unit is equal to or smaller than a predetermined threshold.In some modes, disabling palette mode for the encoding unit includes: disabling palette mode for both the luma and chroma components of the encoding unit, or disabling palette mode only for the chroma component of the encoding unit.

The application discloses a virtual viewpoint image quality evaluation method and system based on double-tree complex wavelet transform. The method comprises the following steps: using an algorithm to perform feature matching on a reference image; performing multi-scale double-tree complex wavelet transform on the matched reference image and a virtual viewpoint image for multiple times to obtain a first wavelet subband set corresponding to the matched reference image and a second wavelet subband set corresponding to the virtual viewpoint image; calculating gradient amplitude similarity between third-level wavelet subbands of the first wavelet subband set and the second wavelet subband set, and using the gradient amplitude similarity to calculate a texture distortion score of the virtual viewpoint image; calculating structural similarity between fifth-level wavelet subbands of the first wavelet subband set and the second wavelet subband set, and using the structural similarity to calculate a structure distortion score of the virtual viewpoint image; and calculating a quality score of the virtual viewpoint image according to the texture distortion score and the structure distortion score. The application can accurately evaluate the quality of the virtual viewpoint image.

To provide methods and apparatuses for video encoding / decoding.SOLUTION: An apparatus for video decoding includes receiving circuitry and processing circuitry. The processing circuitry decodes prediction information of a block from a coded video bitstream, determines whether to allow a palette based coding mode for the block based on a comparison of a size of the block with a threshold, determines whether the block is under a local dual tree structure based on the prediction information, and decodes the block based on the determination of whether to allow the palette based coding mode for the block and the determination of whether the block is under the local dual tree structure.SELECTED DRAWING: Figure 11

The invention provides a dual-tree collaborative HS coding intelligent matching method and device. The method comprises the steps of performing standardization processing on commodity information, and based on the standardized commodity information and structured attribute information, retrieving from a preset HS knowledge base to generate a candidate HS code set; performing branch constraint on the candidate HS code set according to the annotation rule data to obtain at least one compliance candidate subset and a corresponding discrimination attribute missing set; for the compliance candidate subsets, calling a data-driven decision tree to score and sort candidate HS codes in the compliance candidate subsets to obtain at least one target HS code and confidence; and when the confidence coefficient is lower than a preset threshold value and the judgment attribute missing set is non-null, generating supplementary inquiry information for distinguishing candidate HS codes in the compliance candidate subset based on split judgment information of the data-driven decision tree on the compliance candidate subset. According to the method, the HS code matching accuracy can be improved, the compliance interpretability is enhanced, and the manual completion cost is reduced.

Adaptive dual tree coding may be optimized, for example, to implement a trade-off between compression efficiency and encoder complexity. For example, adaptive dual tree / single tree representation in inter slices may be conditioned on characteristics of the slice / picture, e.g., slice type, temporal layer id, and / or temporal depth of the slice being coded / decoded. Use of block-vector guided convolutional cross-component model (BVG-CCCM) may be conditioned on disabling adaptive dual tree and / or characteristics of the slice being encoded / decoded. Use of multi-type tree (MTT) split modes early termination may be conditioned on disabling of adaptive dual tree. In examples, a device (e.g., decoder / encoder) may determine a hierarchical parameter associated with a slice. The device may determine whether to enable a dual tree mode for the slice based on the hierarchical parameter for the slice. The device may decode the slice based on the determination of whether to enable the dual tree mode for the slice.

The present invention relates to an image encoding / decoding method and device. The image decoding method according to one embodiment of the present invention comprises the steps of: determining a tree type of the current unit included in the current slice; dividing a luminance block of the current unit into sub-luminance blocks on the basis of the tree type; and dividing a chrominance block of the current unit into sub-chrominance blocks on the basis of the tree type, wherein the tree type of the current unit is determined as either a single tree or a dual tree, and the current slice is one from among an I slice, a B slice and a P slice.

Disclosed herein are systems, methods, and instrumentalities associated with dual tree coding modes and chroma intra prediction modes reordering. A video coding device as described herein may determine whether a chroma video block is located in an intra-coded region of an inter-coded video slice. Based at least on a determination that the chroma video block is located in the intra-coded region of the video slice and a further determination that a dual tree partition mode is enabled for the intra-coded region, the video coding device may be further configured to determine a plurality of intra prediction modes for the chroma video block, calculate, for each of plurality of intra prediction modes, a respective combined cost associated with predicting the chroma video block and a luma video block co-located with the chroma video block using the intra prediction mode, and reorder the plurality of intra prediction modes based on the respective combined cost calculated for each of the plurality of intra prediction modes. The video coding device may then code the chroma video block based on the reordering of the plurality of intra prediction modes.

The invention discloses a dual-tree genetic programming method for processing a long-tail image classification problem, and the method comprises the following steps: constructing a dual-tree genetic programming individual which comprises a data enhancement tree and a feature extraction tree; setting a staged sampler; performing a multi-generation evolution process, wherein each generation comprises population initialization, individual fitness evaluation, selection, crossover and mutation operation; after the evolution is finished, outputting a dual-tree individual with the highest fitness as a final classification model for classifying a new image; the method is simple and efficient in model deployment and has practical value.

The application belongs to the technical field of computer vision and computer graphics, and discloses a multi-view three-dimensional reconstruction method based on cross-domain feature fusion, equipment and medium, the method comprises the following steps: cross-feature domain coding is carried out on the initial feature token generated by multi-angle images, the coding decomposes the feature into low-frequency and high-frequency components through dual-tree complex wavelet transform, and the amplitude modulation is carried out on the high-frequency component to enhance the details, and the space-frequency fusion feature is generated; the space-frequency fusion features of the multi-angle are weighted and merged through variance embedding, the weight is generated by calculating the variance of each feature token, and adaptive weighted clustering is carried out based on the weight to generate the fused multi-angle feature; three-source attention decoding is carried out on the fused feature, the static embedding is taken as the query, the space-frequency fusion feature is taken as the key, and the fused multi-angle feature is taken as the value, cross-domain attention calculation and up-sampling are carried out, and finally the three-dimensional voxel reconstruction result of the target object is generated.

A compressed bitstream is received. A first syntax element is decoded from the compressed bitstream, indicating whether a luma block and a chroma block associated with a coding unit are to be split using a single tree or a dual tree. The single tree refers to a partitioning structure where the luma block and the chroma block have the same partitioning, and the dual tree refers to a partitioning structure where the luma block and the chroma block have different partitionings. Based on the first syntax element, the luma block and the chroma block are split.

To provide methods and apparatus for video encoding / decoding.SOLUTION: An apparatus for video decoding includes receiving circuitry and processing circuitry, wherein the processing circuitry decodes prediction information of a block from a coded video bitstream, determines whether to allow a palette-based coding mode for the block based on a comparison of a size of the block and thresholds, determines whether the block is under local dual tree structure based on the prediction information, and decodes the block based on the determination of whether to allow the palette-based coding mode for the block and the determination of whether the block is under local dual tree structure.SELECTED DRAWING: Figure 11

The invention discloses a data enhancement method based on dual-tree complex wavelet transform, and mainly solves the problems that a non-stationary signal data enhancement method in the prior art lacks multi-scale analysis capability, cannot fully retain local key features and is insufficient in model generalization capability. According to the scheme, the method comprises the following steps: 1) preprocessing an original signal to enable the original signal to meet the input requirement of dual-tree complex wavelet transform (DTCWT); 2) performing multi-scale decomposition on the signal by adopting DTCWT, and separating a low-frequency approximate component and a high-frequency detail component; 3) selecting a random zero sequence to replace the RZSR or a random noise sequence to replace the RNSR according to an enhancement requirement; 4) generating a random sequence, replacing high-frequency detail components, and meanwhile, retaining low-frequency components; and 5) reconstructing the signal through the inverse DTCWT, generating an enhanced signal, and outputting an enhanced signal. The method can effectively enhance the diversity of data, retains the global characteristics and local detail characteristics of signals, and can be used in the technical field of wireless communication.

This invention discloses a motor fault diagnosis method based on a large language model, belonging to the field of motor fault diagnosis. The method includes: first, collecting three-phase current data; then, using dual-tree complex wavelet transform to extract the amplitude and phase information of multi-layer complex wavelet coefficients as signal fault features, avoiding manual feature selection; next, constructing a multi-layer feature extraction and hierarchical weighted domain adversarial collaborative training framework that integrates grouping and Browsing optimization to extract multi-scale features and enhance domain invariance, thereby improving cross-condition generalization ability; finally, aligning the extracted signal embedding and text embedding across modalities through category-level comparative learning, and fine-tuning the large language model to recognize signal modes. This invention improves fault classification accuracy while enhancing model generalization and achieving textual semantic interpretation of diagnostic results.

The application provides a dual-tree collaborative HS coding intelligent matching method and device. The method comprises: standardizing commodity information, retrieving a candidate HS coding set from a preset HS knowledge base based on the standardized commodity information and structured attribute information; performing branch constraint on the candidate HS coding set according to annotation rule data to obtain at least one compliant candidate subset and a corresponding missing attribute set; for the compliant candidate subset, calling a data-driven decision tree to score and sort the candidate HS coding in the compliant candidate subset to obtain at least one target HS coding and a confidence level; when the confidence level is lower than a preset threshold and the missing attribute set is not empty, generating supplementary inquiry information for distinguishing the candidate HS coding in the compliant candidate subset based on the split discrimination information of the data-driven decision tree on the compliant candidate subset. The application can improve the HS coding matching accuracy, enhance the compliance interpretability, and reduce the artificial completion cost.

The invention discloses a power plant operation robot low-distortion path planning method based on hybrid weighted RRT, and the method comprises the following steps: S1, power plant environment modeling and target setting; s2, performing dual-tree mixed search to generate an initial solution; s3, combining the double trees; s4, single-tree weighted optimization is carried out; s5, path smoothing processing is carried out; and S6, outputting a final navigation path. According to a specific scene of a power plant operation robot, low-distortion path planning is realized through mixed weighted RRT, dual-tree search and single-tree weighted optimization are fused, path curvature continuity is controlled, equipment protection and safety constraints of a power plant are adapted, a low-distortion path is realized, and motion stability of the robot is guaranteed.

An electronic apparatus performs a method of decoding video data. The method includes: receiving, from the bitstream, a plurality of syntax elements associated with a coding unit, the plurality of syntax elements indicating the coding tree type of the coding unit, and whether the local dual tree mode is enabled for the coding unit; and in accordance with the determination that the coding tree type of the coding unit is a single tree, and the local dual tree mode is enabled for the coding unit: disabling the palette mode for the coding unit when the coding unit has the size equal to or less than a predefined threshold. The disabling palette mode for the coding unit may include: disabling the palette mode for both the luma component and chroma component of the coding unit, or disabling the palette mode for only the chroma component of the coding unit.

This invention discloses a method for diagnosing rolling bearing faults, including experimental setup, signal reconstruction, model extraction, fault diagnosis, and verification. The method involves building a rolling bearing fault simulation experimental setup and collecting the original vibration signals from the setup. A dual-tree complex wavelet packet transform is used to decompose the vibration signals into high-frequency wavelet coefficients. Threshold denoising is then applied to these high-frequency wavelet coefficients, and the denoised wavelet coefficients are reconstructed to obtain the denoised reconstructed signal. A cyclic spectrum coherence two-dimensional feature extraction model is established for the reconstructed signal. A multi-scale convolutional layer parallel structure is built using multi-scale convolutional kernels to extract input features at different scales. A multi-scale convolutional neural network is constructed for fault type diagnosis, and the diagnostic accuracy is determined. The diagnostic accuracy of the input and output shaft bearings under different operating conditions is compared to verify the stability and generalization ability of the method. This invention can improve the accuracy of rolling bearing fault diagnosis and has excellent generalization ability.

An image decoding method according to the present disclosure comprises the steps of: deriving residual samples with respect to a target block on the basis of an inverse primary transform with respect to modified transform coefficients; and on the basis of the residual samples, generating a reconstructed picture, wherein a step of deriving the modified transform coefficients may include the steps of: parsing an LFNST index on the basis of the tree-type of a current block not being a dual-tree chroma and a MIP mode not being applicable to the current block; and deriving the modified transform coefficients on the basis of the LFNST index and an LFNST matrix.

A method for decoding an image according to the present document may comprise the steps of: obtaining a modified transformation coefficient; verifying whether the tree type for a current block is a dual-tree chroma; determining whether an MIP mode is applied to the current block on the basis that the current block is not the dual-tree chroma; determining whether an LFNST application width and LFNST application height corresponding to the current block are 16 or more, on the basis of the MIP mode being applied to the current block; and parsing an LFNST index on the basis that the LFNST application width and LFNST application height are 16 or more.

To provide methods and apparatus for video encoding / decoding.SOLUTION: An apparatus for video decoding includes receiving circuitry and processing circuitry, wherein the processing circuitry decodes prediction information of a block from a coded video bitstream, determines whether to allow a palette-based coding mode for the block based on a comparison of a size of the block and thresholds, determines whether the block is under local dual tree structure based on the prediction information, and decodes the block based on the determination of whether to allow the palette-based coding mode for the block and the determination of whether the block is under local dual tree structure.SELECTED DRAWING: Figure 11

This invention relates to the field of remote sensing image compression technology, specifically to a remote sensing image compression method based on dual-tree complex wavelet convolution and a frequency dictionary entropy model. The method includes: compressing remote sensing images using a remote sensing image compression model based on dual-tree complex wavelet convolution and a frequency dictionary entropy model; the remote sensing image compression model includes a dual-tree complex wavelet convolution module, a frequency dictionary entropy model module, and a residual feature extraction module; the dual-tree complex wavelet convolution module is used to perform downsampling and upsampling feature processing on the remote sensing image, effectively removing frequency domain redundancy in the latent representation; the frequency dictionary entropy model module is used to perform frequency division on the obtained latent representation of the remote sensing image to establish a probability model; the residual feature extraction module is used to extract features from the remote sensing image, effectively capturing long-range contextual information. This invention enhances the model's image compression effect by introducing dual-tree complex wavelet convolution and a frequency dictionary entropy model, significantly improving the fidelity of remote sensing images at high compression ratios.

An image decoding method according to the present disclosure may comprise the steps of: determining a tree type; and determining whether to divide a chroma block on the basis of first block division information of the chroma block. Here, when the tree type indicates a dual tree type, the first block division information of the chroma block may be determined on the basis of a first prediction flag decoded from a bitstream, the first prediction flag may indicate whether the first block division information of the chroma block matches a first prediction value, and the first prediction value may be set to a value of first block division information of a luma block corresponding to the chroma block.

Methods and devices are disclosed for coding tree-based synergy between adaptive dual tree and spatial CABAC tuning. The method may include obtaining a coding tree node of a coding tree unit (CTU). The method may further include determining whether to add a syntax element value of the coding tree node to a spatial tuning bin based on a spatial tuning condition. The method may further include decoding a syntax element value associated with a neighboring CTU based on the spatial tuning bin. The spatial tuning condition may be associated with a location of the coding tree node. Determining whether to add a syntax element value of the coding tree node to a spatial tuning bin further may include, based on the location of the coding tree node being at a bottom of the CTU, determining to add the syntax element value of the coding tree node to the spatial tuning bin.

The application is a traffic monitoring image target detection method under adverse weather. The monitoring image to be recovered is input into a dynamic convolution module for convolution processing. After the dynamic convolution module, the image is input into a dual-tree complex wavelet enhancement module. The information enhanced by the dual-tree complex wavelet transform is input into a residual learning recovery module for residual learning to obtain a clean image. The picture output after the residual learning is sent to a YOLOv3 traffic target detection module for target detection. The application uses the dual-tree complex wavelet transform to combine the frequency characteristics and uses the dynamic convolution layer to combine the structural information to mine the robust features in the rain, snow and fog images. The residual network structure is used to refine the obtained features, and the residual learning operation is used to reconstruct the clean image. The application realizes better adaptability to the complex adverse weather scene and is used for the monitoring image recovery in the rain, snow and fog weather.

The invention discloses a path planning method based on a collision heuristic probability random tree. The method comprises the following steps: acquiring an obstacle angular point; performing communication test on the starting point and the ending point to obtain collision point information of the starting point tree and the ending point tree; selecting sampling points from the candidate point set by using a method for generating a probability random sequence based on a collision point distance so as to expand a starting point tree; a time sequence sampling method is used for the end point tree to obtain a sampling point, and connectivity between the sampling point and the latest node of the starting point tree is detected; if so, outputting an initial path, otherwise, switching the dual-tree role to repeat the extension and detection process until the initial path is generated; and acquiring sampling points based on an elliptical constraint axial probability sampling method, and reconnecting nodes in the starting point tree and the end point tree to generate a final path. The method can effectively solve the problem of high time consumption of path planning in a large-scale complex scene, is superior to a traditional method in the aspects of planning efficiency, path quality and algorithm robustness, and has relatively high practicability and popularization value.

The invention discloses a fully-supervised and semi-supervised coronary artery segmentation method based on a direction perception dual-tree complex wavelet, and the method comprises the steps: firstly obtaining a coronary artery computed tomography angiography image, converting the format of the image into an NIFTI format, and completing the preprocessing; then manually labeling the NIFTI format data through an interactive medical image processing system to obtain an accurate structure label of a coronary artery, constructing a coronary artery data set containing labeled data and unlabeled data, and optimizing model parameters through a composite loss function to obtain a high-performance trained XNet-DT segmentation model; and predicting the new CCTA image data by using the trained model, and outputting a coronary artery segmentation mask. According to the method, multi-direction edge perception of the blood vessel is enhanced through DT-CWT, high-precision segmentation under a small amount of annotated data is realized in combination with a semi-supervised learning mode, the problem of difficult segmentation caused by thin coronary artery branches, complex direction and fuzzy boundary is solved, a reliable coronary artery segmentation result can be directly output, and the method is suitable for large-scale popularization and application. Precise technical support is provided for clinical stenosis quantification and operation plan making, and clinical image diagnosis efficiency improvement is assisted.

The invention discloses a method and equipment for generating a main / standby multicast tree, and a medium, and relates to the technical field of communication. The method comprises the following steps: in an initialization stage, defining an original topological graph, a source node, a destination node set, a maximum delay constraint and an iteration threshold value, creating double trees only containing the source node, and binding independent residual graphs respectively to ensure initial resource isolation; a current growth tree is dynamically selected through a random alternate mechanism, a minimum cost path is calculated by using a super node compression technology in combination with a Dijkstra algorithm, a newly added path edge is removed in real time, and a dynamic isolation environment is constructed from another tree remainder graph; in the preferential output stage, the coverage integrity and the total cost are compared through multi-round iteration, the optimal dual-tree combination is reserved, multicast tree optimization which is free of common edges, low in delay and minimum in total cost is achieved, and the network reliability and the calculation efficiency are greatly improved.

The invention discloses a weak light image enhancement method and system based on dual-tree complex wavelet Retinex decomposition. The method comprises the following steps: firstly, decomposing an input image into a low-frequency illumination component and a high-frequency reflection component by using dual-tree complex wavelet transformation; for low-frequency components, a global illumination smoothing module including expansion convolution and global average pooling is designed to accurately estimate and smooth illumination. For high-frequency components, a directional attention mechanism is introduced to enhance texture and edge details. And finally, performing diffusion adjustment and refinement processing on the illumination component and the reflection component to realize self-adaptive reconstruction of the image. According to the method, the brightness, the contrast ratio and the detail visibility of the low-light image can be effectively improved.

The present application relates to a kind of partial discharge signal denoising method combined with singular value decomposition and wavelet transform, belong to signal processing field.The method includes: selecting suitable Hankel matrix is used to construct adaptive singular value decomposition model, responsible for the singular value decomposition of original noisy partial discharge signal;Calculate singular entropy increment, find the position of the maximum bending degree of singular entropy curve according to its asymptotic property;Use the position of maximum curvature as threshold, singular value greater than threshold is used to reconstruct original signal;Select suitable wavelet base function is used to construct one-dimensional two-stage double-tree complex wavelet transform, responsible for the decomposition and reconstruction of signal;Using q-shift scheme joint construction filter bank in DT-CWT interior.The present application can not only inhibit the narrow-band noise and white noise on PD signal well, but also can retain waveform mutation details, while having very low root mean square error and very high waveform similarity in index.