498 results about "Entropy encoding" patented technology

The invention relates to the technical field of computer vision and image recognition, in particular to an image recognition method based on edge computing, which comprises the following steps: dynamically capturing an original image through a plurality of edge nodes, rejecting redundant regions through a multi-modal perception triggering mechanism, and establishing a cooperative processing group. Illumination equalization, noise filtering and resolution self-adaptive compression tasks are distributed according to dynamic role election, a standardized preprocessed image is generated, a lightweight convolutional neural network is operated in parallel to extract a dual-channel feature vector, and after entropy coding lossless compression and equipment identity tag and time sequence stamp attachment, the dual-channel feature vector is transmitted to a cloud end by adopting a lightweight encryption protocol. The cloud end analyzes the data packet, reconstructs a feature topological graph based on space-time relevance, loads a depth residual error recognition model to execute feature fusion and classification decision, feeds back and updates the weight of an edge node model, solves the problems of low collaborative efficiency and feature distortion, and improves the efficiency and precision of image recognition.

Innovations in systems, methods, and software for features of a neural image or video codec are described herein. For example, a neural video encoder can receive a current video frame, encode the current video frame to produce encoded data, and output the encoded data as part of a bitstream. As part of the encoding, the encoder can determine a current latent representation for the current video frame, and encode the current latent representation using an entropy model network that includes one or more convolutional layers. As part of the encoding the current latent representation, the encoder can estimate statistical characteristics of a quantized version of the current latent representation based at least in part on a previous latent representation for a previous video frame, and entropy code the quantized version of the current latent representation based at least in part on the estimated statistical characteristics.

The invention provides an AI large model source network load storage optimization scheduling method and system, and relates to the technical field of intelligent scheduling, and the method comprises the steps: receiving power system source end power generation, power grid transmission, user load and energy storage equipment data, and carrying out the time label alignment and preprocessing to obtain a system feature data set; determining a current operation scene by using a multi-dimensional scene identifier of energy flow decomposition, and calling an expert model combination to generate an initial scheduling parameter; inputting the parameters into a pre-trained large language model, and generating an optimized scheduling parameter set through probability causal reasoning of variational entropy coding; constructing a differential Monte Carlo continuous sampling flow, adjusting the sampling probability density by adopting a neural optimal transmission theory, and screening parameter subsets meeting risk constraints; and according to the market price signal and the operation constraint, determining an optimal scheduling parameter to execute coordinated scheduling, and feeding back an execution result to the model to perform online iterative optimization. According to the invention, intelligent coordinated dispatching of the power system is realized, and the safety and economy of system operation are improved.

A device is configured to decode a mesh from a bitstream that includes the encoded mesh data, wherein, as part of decoding the mesh, one or more processors of the device are configured to determine, based on encoded mesh data, a base mesh that includes a set of vertices; apply the entropy decoding to first, second, and third entropy-encoded data comprises using a shared non-bypass context for entropy decoding at least one bin of each of the first truncated unary (TU) data, the second TU data, and the third TU data, where the first, second, and third TU data are included in binarized representations of syntax elements representing first and second residual values of components of normal vectors of vertices and a second residual value of a component of a normal vector of a vertex.

Decoding a current block includes receiving a compressed bitstream. A transform block of transform coefficients is decoded from the compressed bitstream. The transform coefficients are in a transform domain. The transform block is input to a machine-learning model to obtain a residual block that is in a pixel domain. The residual block is used to reconstruct the current block. Encoding a current block includes receiving a current residual block. The current residual block and a specified rate-distortion parameter are input to a machine-learning model to obtain a quantized transform block. The quantized transform block is entropy encoded into a compressed bitstream.

In one implementation, we propose a scalable framework where a base layer uses NN-based methods to compress the content for computer vision machine tasks and enhancement layer(s) use traditional predictive coding for human viewing. Typically, the based layer performs NN-based analysis to generate a latent tensor, which is entropy coded to produce the base layer bitstream. By performing synthesis on the latent tensor, an inter-layer predictor can be obtained for the enhancement layer(s). Since many machine tasks are not required to be performed for each frame, the base layer may skip analysis for some frames. The synthesis may be performed at the base layer or the enhancement layer(s). In one example, the base layer compresses features optimized for a machine task and the enhancement layer(s) rely on predictive coding. In another example, the enhancement layer(s) can use traditional scalable video compression methods.

The invention discloses a dual-path three-dimensional point cloud compression reconstruction method fusing multi-scale geometric features. The method comprises the following steps: extracting representative skeleton anchor points from original point clouds by adopting farthest point sampling; predicting an octree node occupancy state by using an anchor encoder, and performing entropy coding to generate a skeleton bit stream; a skeleton condition feature encoder is introduced, probability distribution of local features is predicted by using skeleton context priori, cross-path context association is constructed, and a feature bit stream is generated; in the decoding stage, the sparse skeleton point set is restored from the skeleton bit stream, local features are recovered from the feature bit stream in combination with the skeleton structure context, fine-grained reconstruction is carried out on the point cloud through a geometric fusion point cloud up-sampling module, and finally the high-fidelity point cloud is obtained. According to the invention, the point cloud compression effect and reconstruction quality can be improved. The method can be widely applied to the point cloud field.

Provided is a method of decoding coefficients included in image data, the method including determining a Rice parameter for a current coefficient, based on a base level of the current coefficient; parsing coefficient level information indicating a size of the current coefficient from a bitstream by using the determined Rice parameter; and identifying the size of the current coefficient by de-binarizing the coefficient level information by using the determined Rice parameter.

The invention provides a voice reconstruction method and system based on entropy coding residual quantization and frequency spectrum restoration, and relates to the technical field of artificial intelligence voice signal processing, and the method comprises the steps: obtaining an original voice waveform, inputting the voice waveform into a neural voice coding and decoding model, firstly entering a coder to map the input voice waveform into acoustic potential representation, and then entering a frequency spectrum restoration model; performing residual quantization on the acoustic potential characterization layer by layer through a residual vector quantization module, introducing a gating-based dynamic layer number selection mechanism and entropy regularization constraint, enabling bits to be adaptively distributed among different voice segments, reconstructing reconstructed acoustic features of the potential characterization, inputting the reconstructed acoustic features into a decoder, restoring the reconstructed acoustic features into a time domain waveform, and outputting the time domain waveform. And mapping to a logarithmic magnitude spectrum domain through a spectrum repairing module, predicting a residual error in the logarithmic magnitude spectrum domain and performing confidence gating fusion to obtain a complex spectrum, and outputting after time domain synthesis to obtain reconstructed speech. According to the invention, high fidelity, intelligibility and transmission reliability of the voice can be considered at an extremely low bit rate.

The invention relates to the technical field of machine learning, and discloses a feature disassembly and compression method and device, equipment and a storage medium, and the method comprises the steps: obtaining an initial feature of to-be-predicted image data, determining an expert activation weight corresponding to a downstream prediction task based on a hybrid expert network, the initial features are processed through a plurality of expert networks in the hybrid expert network to generate disassembled features, the plurality of expert networks are networks constrained through a low-rank matrix, the disassembled features are quantized to generate quantized features, entropy coding is carried out on the quantized features through a hyper-prior network, and compressed features are obtained. According to the method, the expert activation weight is dynamically adjusted along with task requirements, different task scenes are adapted, initial features are disassembled based on a plurality of expert networks, task irrelevant information is explicitly stripped, task key features are reserved, redundant data volume is reduced, quantized coding is performed on disassembled feature input, code stream self-adaption is realized, and bandwidth occupation is reduced.

The invention discloses an entropy coding compression method for high-dimensional sparse data, which relates to the technical field of data compression, and comprises the following steps: reading an original high-dimensional sparse matrix, extracting a position index set and a corresponding non-zero value set of all non-zero elements, extracting active samples from the non-zero value set, and compressing the active samples. After an active sample matrix and an optimal mean value centralization matrix are constructed, principal component projection and a self-expression structure are introduced for joint modeling, a low-rank robust optimization objective function is formed, and a principal component feature matrix is finally output by alternately optimizing mean values, projection, weights and residual errors. According to the method, the compression efficiency and the processing pertinence of high-dimensional sparse data are effectively improved, self-expression structure modeling and residual regular optimization between samples are further combined, the structure consistency is kept in the dimension reduction process, a key information structure is kept while the compression ratio is guaranteed, and the high-fidelity and low-redundancy entropy coding compression effect is achieved.

The invention provides a lossless compression method and decompression method for power grid waveform data, equipment, a medium and a program product, and the method comprises the steps: carrying out the periodic feature analysis of the original sampling data of a power grid waveform, so as to determine the periodic structure of the original sampling data, and carrying out the segmentation processing of the original sampling data based on the periodic structure; for the sampling data in each segment, extracting differential information between adjacent sampling points to form a differential data sequence; dynamically determining a corresponding quantization parameter based on the statistical distribution characteristic of the differential data sequence, and performing adaptive quantization processing on the differential data sequence to generate quantized differential data; and entropy coding processing is carried out on the quantized differential data to generate compressed data used for representing the original sampling data, and characteristic parameters used for reconstructing the original sampling data are stored in the compressed data in an associated mode. Unification of high compression ratio, low power consumption and strict lossless reconstruction is realized, and the application requirements of long-term monitoring and remote transmission of the edge side can be met.

The invention discloses a millimeter wave radar point cloud compression method based on heterogeneous representation and an implicit neural network. Firstly, point cloud fine geometric features are extracted through a point-based compression network, global semantics are aggregated through a voxel-based compression network, and point-voxel heterogeneous joint representation and preliminary compression are realized. Secondly, constructing an adaptive octree to code a compressed data space structure to generate a partitioned bit stream, and performing statistical compression on the voxel-level high-dimensional features by using context-aware entropy coding to generate a feature bit stream; then, joint transmission is performed on the partition bit stream, the feature bit stream and the neural network weight for implicit representation. And finally, decoding and recovering the coarse-grained point cloud at a receiving end, inputting the coarse-grained point cloud and a neural network weight into a point-based synthesis network based on implicit neural representation, and finally reconstructing a high-fidelity point cloud through continuous surface modeling and detail compensation. According to the method, the compression efficiency and the reconstruction quality of the millimeter wave radar point cloud under the low code rate are remarkably improved.

A method for adaptive loop filtering is provided that includes determining a coefficient value for each coefficient position of an adaptive loop filter, applying the adaptive loop filter to at least a portion of a reconstructed picture using the coefficient values, and entropy encoding coefficient values into a compressed bit stream using predetermined short binary codes, wherein the short binary code used depends on the coefficient position of the coefficient value.

A method for encoding a point cloud to generate a bitstream of compressed point cloud data is provided. The point cloud's geometry is represented by an octree-based structure with a plurality of nodes having parent-child relationships by recursively splitting a volumetric space containing the point cloud into sub-volumes each associated with a node of the octree-based structure. The method includes: determining a coding mode, wherein the coding mode includes a planar coding mode and an angular coding mode; obtaining coding context information for a present child node, entropy encoding the present child node based on the obtained coding context information to produce encoded data for the bitstream.

The invention discloses a multi-modal feature adaptive fusion and compression semantic communication and classification method and device, and the method comprises the steps: carrying out the multi-modal feature extraction of a collected multi-modal signal, and obtaining a multi-modal feature; carrying out adaptive fusion on the multi-modal features to obtain fused features; and entropy coding compression is performed on the fused features to obtain fused compressed features, and the fused compressed features are converted into binary code streams through an encoder-decoder mechanism for realizing semantic communication with a task module. The method has the advantages of being high in fusion efficiency, friendly in compression, low in calculation overhead, small in communication cost and bandwidth occupation and the like, and the dual requirements for intelligent sensing and task execution capacity under the condition that the bandwidth is limited or the computing power is limited are met.

The embodiment of the invention provides an end-to-end image compression method and system based on window local attention and generalized chessboard space channel context, and belongs to the technical field of image processing. The method comprises the following steps: constructing a transformation network based on an attention module and a stacked residual block; the transformation network based on the attention module and the stacked residual block is used for executing adaptive transformation of contents through dynamic representation and neighborhood information embedding to obtain potential features; establishing a generalized chessboard space channel context model; the generalized chessboard space channel context model is used for carrying out entropy coding on the potential features; and obtaining image compression data according to the transformation network based on the attention module and the stacked residual block and the generalized chessboard space channel context model. According to the method, redundancy can be eliminated to the maximum extent, excellent rate distortion performance is achieved, and meanwhile high-throughput parallel computing efficiency is ensured.

Systems, apparatuses, methods, and computer-readable media are described for coding RAHT coefficients based on coefficients of neighboring nodes. An encoder may use a forward RAHT transform to obtain all RAHT coefficients and may entropy encode all coefficients in the bitstream. A decoder may decode all coefficients and then backward RAHT transform the decoded coefficients to obtain attributes. A coder (e.g., encoder or decoder) may use already-coded coefficients of neighboring RAHT nodes to select a context and entropy code coefficients of a current RAHT node based on the selected context.

The invention discloses a video code rate dynamic allocation compression method based on content complexity prediction, which comprises the following steps of: S1, acquiring a video frame sequence, and preprocessing; s2, inputting the frame-level feature tensor into a gated residual convolutional network, and outputting a complexity prediction sequence; s3, constructing a frame priority queue, and calculating the complexity jump amplitude between adjacent frames; s4, a compression area is divided, and a corresponding code rate resource scale factor is allocated; s5, configuring a reference frame structure, a prediction interval and an initial quantization step size for each compression region, and calculating a region target bit number; s6, distributing regional bits to each frame in a compression coding process, and dynamically adjusting a frame-level quantization parameter and an entropy coding strategy; and S7, after compression is completed, reversely updating convolution prediction network parameters through bit distribution errors. According to the invention, fine code rate dynamic allocation and adaptive compression control based on content complexity are realized, and the video compression quality and bit utilization efficiency are effectively improved.

The invention discloses an image compression method and system based on edge gradient self-adaption, and the method comprises the steps: converting an input image into a YCbCr color space, calculating an edge gradient value of a brightness component, and employing iteration processing including a feedback mechanism: dividing an edge region and a non-edge region based on a current self-adaption edge gradient threshold value, the blocks are divided according to different sizes; dynamically updating an edge gradient threshold according to a block statistics result, and adaptively optimizing region division through multiple iterations; and finally, based on the optimized blocking result, processing the edge region and the non-edge region by adopting different quantization strategies, generating a quantization matrix, and then carrying out entropy coding to output a compressed code stream. According to the method, adaptive adjustment of compression parameters is realized through an iterative optimization mechanism, image edge and texture details are effectively reserved while a high compression rate is ensured, and the subjective visual quality of a compressed image is remarkably improved.

A method and an apparatus including processing circuitry are provided. The processing circuitry determines previous probability information associated with each entropy coded region of multiple regions in a previous picture. The processing circuitry selects, based on (i) a location or a quantization parameter of an independently decodable coding segment in a current picture or (ii) syntax information of the independently decodable coding segment, a region among the multiple regions. Initial probability information for one or more current syntax elements of a block in the independently decodable coding segment is determined based on the previous probability information associated with the selected region. The one or more current syntax elements are first to be entropy decoded in the independently decodable coding segment. The processing circuitry entropy decodes coded bits associated with the one or more current syntax elements into a bin string based on the initial probability information.

The invention relates to the technical field of virtual reality, and discloses a touch display screen panoramic interaction method based on virtual reality. The method comprises the following steps: deploying a tactile sensing network on the surface of a touch display screen, collecting space coordinates and pressure data of a touch point in real time, and synchronously obtaining a computing resource utilization rate and network bandwidth data of a virtual reality processing node; classifying the touch data to generate behavior mode labels, and determining an optimal touch point distribution set by using a dynamic load balancing algorithm in combination with resource data; performing normalization and entropy coding compression on the original interaction data stream to generate a standardized interaction data packet; transmitting to a temporary buffer area of the distributed database, activating a persistent trigger, acquiring a storage node state through a log synchronization module, and determining an optimal path for fragmentation storage. According to the method, multi-dimensional data are integrated, resource allocation and data processing storage are optimized, and the real-time performance and stability of virtual reality interaction are enhanced.

The invention provides an immersive video coding method and system based on 3DGS, and the method comprises the steps: carrying out the sparse reconstruction of each frame of multi-view video data, and obtaining an initial point cloud; determining anchor points of three-dimensional Gaussian distribution in each frame; extracting spatial context information of the anchor points through multi-resolution hash coding, and splicing the spatial context information with the features of the anchor points to form fusion features; predicting parameters of three-dimensional Gaussian distribution corresponding to each anchor point through a neural network by using the fusion features and camera parameters, and obtaining a rendered image; calculating the color loss between the rendered image and the original video frame, and optimizing the parameters of the anchor points; performing quantization and entropy coding on the optimized parameters of the anchor points; in combination with the color loss and the coding rate, performing rate distortion optimization on the quantization parameter to generate compressed three-dimensional scene representation; and repeating the steps for each frame of the multi-view video, and finally outputting a compressed immersive video code stream. According to the invention, high-quality representation and efficient compression of the immersive video are realized, and the rate-distortion performance is improved.

In end-to-end compression, a deep neural-network based encoder can be used to encode an image. The embeddings output from the encoder are quantized and encoded with a lossless encoder. Advantageously, at least one embodiment allows improving the latent entropy coding by further reducing the redundancies in the quantized latent. To that end, at least one embodiment discloses taking into account channels importance by coding an indication of a channel activity (or significance): performing post-conditional entropy coding by computing conditional probability based on a context afterwards: using channels reordering to improve inter channel correlation: or performing RDOQ like process by optimizing the main latent for a particular image.

The invention relates to a man-machine mixed vision-oriented semantic perception video compression method and system, and the method comprises the steps: extracting the dynamic semantics of a video sequence, and generating a region of interest; generating a focusing frame with consistent vision according to the input frame and the corresponding interested area mask; predicting feature probability distribution of the focusing frame through an entropy model, and compressing the feature probability distribution into a code stream; decoding the code stream through a conditional decoder to obtain a semantic compressed reconstructed video; performing feature alignment on the decoded frames in the decoded frame buffer areas of the basic branch and the auxiliary branch to generate prediction features; inputting the prediction frame of the prediction feature and the video sequence into an entropy model, and compressing the prediction frame and the video sequence into a code stream through entropy coding; decoding the code stream to obtain reconstruction features; and converting the reconstruction features into fine reconstruction features to obtain a final compressed and reconstructed video. Compared with the prior art, the method has the advantages that high machine vision task accuracy can still be maintained under the condition of low code rate, and higher rate accuracy performance is achieved in the machine vision task.

To enable the decoding of data in a variable-length code sequence compressed using entropy coding with low latency.SOLUTION: A decoding device is configured to acquire a predetermined number of bits of data per clock cycle from a variable-length code sequence data encoded using entropy coding, and decode the predetermined number of bits of data per clock cycle using reference information obtained from the multiple predetermined numbers of bits of data.SELECTED DRAWING: Figure 1

The invention discloses a deep learning image compression method and system based on wavelet domain double branches, and the method comprises the steps: carrying out the coding and decoding through a deep neural network in combination with the wavelet domain features of high-frequency and low-frequency double branches, carrying out the coding and mapping of an original image to a compact potential feature, carrying out the super-prior coding, quantization and entropy coding, so as to generate a code stream, and carrying out the compression of a deep learning image. Global context information is obtained through hyper-prior decoding, channel division is performed on the compact potential features, and context modeling based on space and channels is performed on each channel block by using the global context information so as to predict a mean value and a standard deviation of the channel blocks obeying Gaussian distribution, and the mean value and the standard deviation are used for guiding quantization and entropy coding of the channel blocks; and generating a code stream after image compression, mapping the potential features obtained by decoding back to the reconstructed image, and constructing rate distortion loss based on the control code rate of the potential features after decoding, the control code rate of super-prior decoding and the distortion of the original image and the reconstructed image so as to train a deep neural network for image compression.

The invention provides an intelligent compression transmission method and system for a message body, and the method achieves the efficient compression and intelligent transmission of a structured message through the technical means of structured data templated compression, type-aware entropy coding, network quality real-time monitoring, dynamic compression strategy decision and the like. The compression strategy can be adaptively adjusted according to the dynamic change of the network environment, and the data transmission efficiency is improved.

The invention relates to a three-dimensional point cloud prediction geometric coding method based on deep learning, and the method comprises the steps: 1, forming a prediction tree through points collected by each laser transmitter, and converting an original laser radar point cloud LPC into a plurality of prediction trees for representation; 2, respectively designing different predictors and entropy encoders for each component of the coordinates of the points, and compressing each component of the coordinates of the points by applying different quantization step lengths; 3, selecting a quantization step size for quantifying each component by adopting a quantization step size selection strategy; 4, adopting an entropy model to model the probability distribution of the residual error of each component so as to encode the residual error entropy; and step 5, decoding is realized through a reverse process from the step 1 to the step 4. Compared with other methods, the method provided by the invention obtains the best rate distortion performance.

The embodiment of the application provides a kind of quantization parameter coding method and electronic equipment, the coding method includes: first, according to the QP reconstructed value of the QP of coded non-private CU in CU QP group, determine the QP prediction value of non-private CU to be coded in CU QP group;Then, according to the QP original value of non-private CU to be coded and the QP prediction value of non-private CU to be coded, determine the QP residual of non-private CU to be coded;Subsequently, according to the number of coded non-private CU in CU QP group, determine the context model corresponding to the QP residual of non-private CU to be coded;After that, according to the context model corresponding to the QP residual of non-private CU to be coded, the QP residual of non-private CU to be coded is entropy coded. In this way, it can be guaranteed that the decoding process of the QP of non-private CU at the decoding end and the encoding process of the QP of non-private CU at the encoding end are consistent.