1249 results about "Image compression" patented technology

The present disclosure provides a variable-bit-rate image compression method and system, an apparatus, a terminal, and a storage medium. The variable-bit-rate image compression method includes: obtaining an initial feature map from a to-be-encoded image; quantizing the initial feature map by a dead-zone quantizer; performing entropy encoding on the quantized feature map and hyper-prior information to obtain a compressed bit-stream; performing entropy decoding on the compressed bit-stream, and recovering quantized hyper-prior information and the quantized feature map; performing inverse quantization on the quantized feature map to obtain a reconstructed feature map; obtaining a reconstructed image from the reconstructed feature map; and adjusting quantization and inverse quantization parameters according to a target bit-rate or target distortion. The present disclosure provides a precise bit-rate control solution, makes the bit-rate of the compressed bit-stream better adapt to the dynamic change of a network bandwidth, and has an extremely high actual application value.

The invention discloses a multi-scale semantic guidance image compression method and system and a storage medium, and the method comprises the following steps: obtaining input image data, carrying out the preprocessing of an input image, and obtaining standardized image data; inputting the standardized image data into a pre-trained semantic segmentation network to generate a multi-scale semantic feature map and a semantic weight map corresponding to the multi-scale semantic feature map; a three-stage pyramid encoder is constructed, and the standardized image data is subjected to the following steps of: sampling under depth separable convolution to generate multi-scale features; the reversible neural network carries out nonlinear transformation on the multi-scale features; the multi-scale feature subjected to nonlinear transformation is decomposed into a low-frequency sub-band and a high-frequency sub-band through adaptive discrete wavelet transformation, dynamic selective state space modeling is executed on the high-frequency sub-band based on a semantic weight map, and a compressed code stream is generated; and inputting the compressed code stream into a decoder, decoding based on a lightweight Mama module, and reconstructing an image in combination with inverse wavelet transform and a semantic weight map.

The invention discloses a power transmission image compression quality evaluation method based on multichannel fusion, belongs to the technical field of smart power grids, and solves the problem of how to enhance adaptive evaluation performance of image quality in scenes with different compression ratios. A multichannel feature processing module introduces learnable offset to realize dynamic alignment and effective fusion of multichannel features; the multi-scale attention fusion module is combined with multi-scale feature extraction and an attention mechanism, learnable position codes are introduced, and the sensitivity to local structure changes is enhanced while the global perception ability is ensured; the self-adaptive quality evaluation module captures different scale features and local information by constructing residual connection and a multi-branch structure, performs weighted fusion on multi-channel fusion features in combination with a dynamic weight generation mechanism, and realizes accurate judgment of the quality of a complex scene image under different compression levels; while the image compression distortion perception capability is improved, the adaptive evaluation performance of the image quality in scenes with different compression ratios is effectively enhanced.

The invention discloses a generative invisible watermarking method based on a stable diffusion model, which comprises the following steps of: processing a text prompt / image prompt to obtain a latent variable, guiding to generate an image by using the latent variable, converting the image into a low-dimensional potential representation through a variational auto-encoder, generating potential noise according to the low-dimensional potential representation, and generating a stable diffusion model according to the potential noise. Performing multiple iterations by combining the potential noise and the low-dimensional potential representation to generate a noise-containing image; a watermark decoder is utilized to finely adjust the decoder, so that the finely-adjusted weight watermark is embedded into the generated image; and meanwhile, when the stable diffusion model generates an image, compressing the image into potential noise by using a variational auto-encoder, then performing wavelet transform on the obtained potential noise to obtain a noise watermark, mapping noise watermark information into an annular pattern watermark, embedding the annular pattern watermark into a noise low-frequency sub-band, and performing image generation by using the watermark-containing noise to obtain a watermark-containing image. According to the method, the watermark is embedded in the image generation process, and the watermark information in the generated image can be extracted.

The invention discloses a panoramic video frame insertion method based on a potential diffusion model. The method comprises the following steps: compressing an input image to a potential space by using a panoramic perception vector quantization variational auto-encoder to obtain potential features; constructing initial noise, and fusing the motion features extracted by the panoramic optical flow adapter to obtain condition information; performing iterative denoising operation on the potential features of the intermediate frame to obtain final potential features of the intermediate frame; and restoring the final potential features of the intermediate frame into a frame insertion image of a pixel space through a condition decoder. According to the panoramic video frame interpolation method provided by the invention, the potential diffusion model and the panoramic characteristic enhancement technology are combined, so that the perception quality of a frame interpolation result can be remarkably improved, details and complex textures of a pole region can be better reserved, and a high-quality time interpolation solution is provided for immersive panoramic video application.

A computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of: (i) receiving an input image at a first computer system; (ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation; (iii) quantizing the latent representation using the first computer system to produce a quantized latent; (iv) entropy encoding the quantized latent into a bitstream, using the first computer system; (v) transmitting the bitstream to a second computer system; (vi) the second computer system entropy decoding the bitstream to produce the quantized latent; (vii) the second computer system using a second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image.

The invention relates to the technical field of image compression, in particular to a hierarchical multi-context space adaptive image compression method. The method comprises the steps of obtaining a training set and a test set; constructing a spatial adaptive feature modulation network, wherein the spatial adaptive feature modulation network comprises an encoder, a decoder, a super-prior encoder and a super-prior decoder; constructing a multi-context joint entropy estimation model, wherein the multi-context joint entropy estimation model comprises a local context model, a channel context model, an in-layer anchor point context model and a cross-layer global context model; obtaining an image compression network in combination with the spatial adaptive feature modulation network and the multi-context joint entropy estimation model; respectively training and testing an image compression network by using the training set and the test set to obtain a trained image compression network; and inputting a to-be-processed image into the trained image compression network to obtain a reconstructed image. According to the invention, the image compression effect is improved.

The present invention relates to a data processing method based on an edge AI computing and storage integrated chip, comprising the following steps: inputting image data to be processed into a preset edge AI computing and storage integrated chip for data classification to obtain sub-image data to be processed; identifying the sub-image data to be processed to determine whether there is an abnormal situation in the sub-image data to be processed, and if so, marking the sub-image data to be processed based on the abnormal situation to obtain a marked abnormal situation image; performing image compression processing on the marked abnormal situation image to obtain abnormal image compressed data; performing abnormal level classification on the abnormal image compressed data to obtain an abnormal classification result; prioritizing the abnormal situation based on the abnormal classification result to obtain an abnormal event priority sequence table, which solves the technical problem that the computing power and storage space of traditional chips are relatively limited, which limits the processing capacity of complex data sets.

The embodiment of the invention discloses a model training method and device. The method comprises the following steps: inputting a training image into an encoder in a pre-training auto-encoder to obtain a first compressed image code, and inputting the training image into a target visual basic model to obtain a second compressed image code; wherein the pre-training auto-encoder comprises an encoder and a decoder; determining a comparison loss value according to the first compressed image code and the second compressed image code, and taking the comparison loss value and at least one other loss value as a target loss value; wherein at least one other loss value is a loss value reflecting the performance of the pre-trained auto-encoder; and performing training optimization on the pre-training auto-encoder based on the target loss value. According to the scheme, the pre-trained auto-encoder can be trained and optimized by taking the image compression result of the target visual basic model as a reference, so that the encoding and decoding effects of the auto-encoder are improved, and more and more accurate original image information can be obtained through the auto-encoder.

A heavy traffic abnormal event detection and state discrimination system belongs to the field of intelligent traffic and comprises a data acquisition and labeling module, an image processing module, a traffic state analysis module, a state determination and abnormal event identification module and a transfer learning module. The data acquisition and labeling module comprises a data acquisition unit and a data labeling unit; the image processing module comprises an image enhancement unit and an image compression and reconstruction unit; the traffic state analysis module comprises a traffic bottleneck identification unit and a traffic flow wave analysis unit; the state judgment and abnormal event recognition module comprises a vehicle statistical unit, a congestion state recognition unit, a state transition analysis unit and a compressed sensing model establishment unit; and the transfer learning module comprises a transfer learning unit. According to the method, the false detection rate of the traffic flow abnormal events in bad weather can be reduced, so that the traffic abnormal events can be detected all day long, and the occurrence probability of the traffic events in bad weather conditions can be reduced.

The invention provides a real-time video image compression method based on deep learning, and relates to the technical field of video image compression, and the method comprises the steps: carrying out the key feature recognition through employing an attention mechanism; performing convolution training optimization on the video image sample data set by using a deep learning network structure; a self-encoder structure is designed to carry out feature map encoding compression; a video image compression adaptive network is generated through series fusion; a real-time video image frame is collected for preprocessing, and feature compression processing is performed on a standard video image frame based on a video image compression adaptive network. According to the method and the device, the technical problem that the video compression quality is reduced due to the fact that the generalization ability is insufficient in the face of various scenes and the video compression strategy is difficult to adaptively adjust according to different scenes in the prior art can be solved, the adaptive network is constructed through the combination of deep learning and the auto-encoder, and the video compression quality is improved. And the video compression strategy is dynamically adjusted according to the contents of different video images, so that the video compression quality is improved.

The invention belongs to the field of image / video compression, and discloses an intelligent image compression encoder based on a conditional reversible neural network, which comprises an image enhancement module, a reversible multi-frequency fusion network RMFFN and an entropy model, and is characterized in that the image enhancement module comprises a multi-expansion channel refiner module MDCR and an expansion residual attention module RDAM; the image enhancement module optimizes input features and constructs a conditional reversible neural network by using a flow model, namely, multi-stage nonlinear mapping is realized by stacking four reversible multi-frequency fusion networks; the super-prior codec of the entropy model extracts hidden variable features by stacking multi-scale residual attention blocks, and introduces a discrete Gaussian mixture likelihood model in an entropy coding stage. According to the method, high-fidelity reconstruction is still kept at a low bit rate, and the technical problems of bit rate-distortion balance, high-frequency detail retention and calculation efficiency of a traditional method are solved.

A system and method for compressing synthetic aperture radar (SAR) images with enhanced phase recovery and unwrapping capabilities is disclosed. The system performs preprocessing on input SAR images, applies discrete cosine transform (DCT) to create subbands, and utilizes a multi-pass amplitude compression technique. A specialized neural network performs phase unwrapping using compressed amplitude information and interferogram wrapped phase data. The system employs a channel-wise transformer fusion block (CTFB) for feature fusion and a multi-stage context recovery subsystem with optimized loss functions for both amplitude and phase recovery. The method achieves improved compression efficiency and phase recovery accuracy, particularly beneficial for Interferometric SAR (InSAR) applications.

The invention discloses a cross-modal medical image registration method based on a submerged space diffusion model, relates to the technical field of medical image processing, and solves the technical problem that an existing registration method is not suitable for multi-modal medical image registration. The method comprises the steps of obtaining a first modal original medical image and a second modal original medical image, and performing preprocessing operation to obtain a floating image and a target image; constructing a cross-modal conversion network, compressing a target image to a submerged space for representation by using a pre-trained auto-encoder, inputting the target image into a diffusion model, and performing training through forward noise addition and reverse noise reduction; inputting the floating image into a diffusion model of a cross-modal conversion network to generate a second modal conversion image; inputting the floating image and the target image into a registration network, and obtaining respective registered images for the floating image and the second modal conversion image; and training the registration network to obtain an image after floating image registration. The method is wide in application field, and is suitable for registration among medical images in various modes.

A vector quantization (VQ) neural network-based image compression method includes encoding, by a first encoder, a first image to obtain a first latent feature corresponding to the first image; generating, based on the first latent feature and using a leading codebook, a leading codebook indices map and a first codeword map corresponding to the leading codebook indices map, wherein the leading codebook comprises codebook indices that are assigned to identical vectors in multiple codebooks; encoding the leading codebook indices map to generate an encoded leading codebook indices map; and transmitting the encoded leading codebook indices map to a decoder.

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional autoencoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional autoencoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and denoising. The models trained on the MNIST handwritten-digit and CIFAR-10 image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%.

The invention discloses a sparse matrix processing method and device in an image recognition process, equipment and a medium, and relates to the field of computer image processing, and the method comprises the steps: inputting a feature image into a convolutional neural network; if the convolution kernel meets a preset sparse matrix condition, performing structured sparseness on the convolution kernel to obtain a sparse matrix, compressing the sparse matrix by using an improved compression sparse row format to obtain a compression matrix, and constructing an index matrix of the compression matrix; storing the feature image, the compression matrix, the index matrix and the preset bias matrix in a global memory, activating a target thread bundle in the computing core, and distributing the target thread bundle to a target data processing channel; loading the compression matrix and the index matrix to a shared memory corresponding to the target data processing channel by using the target thread bundle, and loading the feature image and a preset bias matrix to a register file; and executing the operation instruction to read the current matrix operation data from the shared memory and the register file to the matrix calculation unit to complete the matrix multiplication and addition operation.

The present invention relates to a method, system and readable storage medium for allocating bitrate in image compression, the method comprising: evenly dividing an image to be encoded into a plurality of image blocks; using a plurality of texture complexity statistical algorithms to calculate a plurality of measurement indicators for measuring texture complexity of each image block, and fusing the plurality of measurement indicators of each image block in combination with the optimal human eye subjective evaluation result to obtain the fused texture complexity of each image block; allocating bitrate to each image block based on the encoding order of the image to be encoded, and allocating bitrate to each image block according to the maximum total bitrate under the limitation of storage space or transmission channel bandwidth and the fused texture complexity of each image block. The present invention combines the advantages of different texture complexity statistical algorithms and the optimal human eye subjective evaluation result to fuse a plurality of measurement indicators to allocate corresponding bitrates to different image blocks, and can minimize the bitrate required for compression under the premise of ensuring the subjective effect of reconstructing the image.

Systems, methods, and instrumentalities are disclosed herein for reducing the amortization gap in end-to-end image compression and / or video compression. In examples, a video decoder may obtain an entropy model indication in video data. Based on the entropy model indication, the decoder may determine an entropy model to use for decoding a current picture. The current picture may be decoded based on the determined entropy model. In examples, the entropy model indication may indicate whether to use an updated entropy model or a prior entropy model for decoding the current picture. In examples, the entropy model indication may indicate an updated entropy model or a learned entropy model to use for decoding the current picture.

The invention relates to a 5G broadcast television image communication system fused with deep learning and a method thereof. The system comprises an image processing module, a channel processing module, a data transmission module, a channel decoding module, an image reconstruction and enhancement module and a system optimization and self-adaption module. Through an image compression technology based on Vision Transform, an image is divided into image blocks with a fixed size, and a multi-head attention mechanism is utilized to extract global context and local features, so that efficient compression is realized. Meanwhile, the channel coding and decoding unit based on Transform enhances the anti-noise capability of the system by generating redundant bits and correcting cross-layer error codes, an image reconstruction and enhancement module is combined with a generative adversarial network (GAN) and a super-resolution model, detail compensation and enhancement can be carried out on the decompressed image, and through a system optimization and self-adaptive adjustment module, the image reconstruction and enhancement module can carry out self-adaptive adjustment on the image. A transmission strategy is dynamically adjusted according to a channel state and transmission feedback, and efficient and stable radio and television image communication is realized in a complex 5G network environment.

The invention discloses an underwater robot visual image compression, decompression and transmission method and device. The method comprises the steps of constructing an image compression model used for underwater robot visual image compression, training the image compression model, constructing a visual image coding end based on the trained image compression model, performing compression coding on the underwater robot visual image by using the visual image coding end, generating code stream data, and outputting the code stream data. And constructing a visual image compression end based on the trained image compression model so as to complete compression of the visual image of the underwater robot, and constructing a visual image decoding end based on the trained image compression model, the visual image decoding end being used for decoding the code stream data and reconstructing the image so as to generate a reconstructed visual image of the underwater robot. The underwater robot visual image compression and decompression method provided by the invention is high in compression ratio and good in image reconstruction performance, and can be applied to compression and transmission tasks of underwater robot visual images.

A method includes receiving a bitstream that comprises coded information of a current block, the coded information of the current block indicates a state transition path of a state machine, the state transition path of the state machine includes at least a first state transition associated with a first quantization shifting offset of one or more first transform coefficients in transform coefficients of the current block. The method also includes determining the first quantization shifting offset associated with the one or more first transform coefficients according to the first state transition; reconstructing the one or more first transform coefficients based on the first quantization shifting offset; calculating residuals in a spatial domain of the current block based on at least the one or more first transform coefficients; and reconstructing the current block according to the residuals in the spatial domain.

The invention discloses a code rate adaptive image compression method and system, and the method comprises the steps: obtaining an input image, and calculating the local information entropy of the input image to generate a spatial adaptive mask; obtaining target code rate and actual code rate information to generate a code rate control signal; and dynamically selecting a calculation path by using a mask through a dynamic reversible neural network, and executing reversible quantization transformation according to the control signal to obtain a compressed bit stream and actual code rate information for closed-loop feedback. According to the method, a symmetric reversible framework with shared parameters is constructed, so that the model storage requirement is reduced; the calculation depth of the network is dynamically adjusted through entropy sensing gating, and the overall calculation amount is reduced; and a composite control and PID optimization mechanism is adopted, so that continuous and smooth code rate control is realized. The deployment and application efficiency of the compression system in a resource limited scene can be effectively improved.

An attention degree estimation section in a compression coding section of a server estimates an attention degree on the basis of contents indicated by a moving image generated by an image forming section, for each of unit regions produced by dividing a frame plane. A compression coding processing section compression-codes the moving image at a compression rate varied in the frame plane according to a distribution of the attention degrees. A communication section transmits compression-coded data to an image processing apparatus.

The invention provides a hyperspectral remote sensing image compression method based on attention and quantization coding optimization, and the method comprises the steps: carrying out a network model training process: carrying out the processing, cutting and enhancement of hyperspectral remote sensing image data, and constructing a sample set for training; extracting low-dimensional feature representation of the sample data by using a lightweight encoder, wherein the encoder integrates a convolutional layer and a spectrum multi-head self-attention module; a decoder fusing a space-spectrum attention mechanism is adopted to gradually reconstruct a hyperspectral remote sensing image from low-dimensional features; optimizing coding and decoding model parameters through a combined loss function; a quantization coding two-stage compression process: performing adaptive quantization on the features, and mapping the floating point type features into discrete integers based on a logarithm mapping strategy; performing two-stage coding compression on the quantized features; and recovering feature representation through decoding and inverse quantization, and inputting a trained decoder network to reconstruct a hyperspectral remote sensing image.

The invention belongs to the technical field of image encryption, and discloses a medical image compression and encryption method and system based on a memristor FHN neuron model, and the method comprises the steps: fusing n color or gray medical images of any size into an M * N * 3 fusion image; sparse representation is carried out on the fused medical image in combination with discrete wavelet transform, and redundant data are reduced; initial conditions and control parameters of an m-FHN chaotic system are generated through an SHA-512 hash value of an original image, and strong association of a secret key and a plaintext is ensured; the m-FHN system is iterated to generate three groups of chaos sequences, and the chaos sequences are quantized to obtain a pseudo-random matrix for diffusion and scrambling operation; performing forward diffusion, index scrambling and backward diffusion operation on the sparse image in sequence to obtain a final compressed and encrypted image; a receiving end acquires an initial parameter and a control parameter bound with a plaintext through a secure channel, and then performs inverse backward diffusion, inverse index scrambling, inverse forward diffusion and inverse discrete wavelet transform on a ciphertext image in sequence to obtain a decrypted image.

The invention provides an image compressed sensing joint reconstruction method and system, a storage medium and electronic equipment. The image compressed sensing joint reconstruction method comprises the following steps: acquiring an original image, and acquiring an image vector based on the original image; performing primary reconstruction and secondary reconstruction on the image vector to obtain an initial reconstruction image; and further performing image post-processing on the initial reconstructed image based on the fine tuning network to obtain a target reconstructed image. The method not only pays attention to observation in an ideal environment, but also considers the influence of noise and other degradation factors in a reconstruction process, so that the capability of accurately deducing image features and modes in a noisy environment of the model is remarkably improved, and the robustness of a reconstruction algorithm is enhanced; moreover, the quality of the initial reconstructed image is optimized, the reconstruction error is reduced, the target reconstructed image is closer to the original image, and the reconstruction accuracy and visual effect are improved.

The invention relates to the technical field of image compression processing. The invention provides a video compression processing method and device. The method comprises the following steps: performing video feature extraction on a to-be-processed video, wherein video features comprise space complexity, time complexity and color complexity; configuring the size of a target file corresponding to the to-be-processed video, and determining the size of each target file according to a specific scene and a user demand; dynamically generating compression parameters through weighted calculation based on the extracted video features and the determined size of the target file; and performing dynamic evaluation according to the video compression effects under different compression parameters to determine the range of the optimal compression parameter, selecting the optimal compression parameter from the determined range of the optimal compression parameter, and performing video compression on the to-be-processed video according to the selected optimal compression parameter. According to the invention, the optimal compression parameter corresponding to the to-be-processed video can be determined, and more efficient and accurate video compression can be realized.

An image processing method for extracting a subject from an image including the subject using a background image includes: generating a background removed image obtained by removing a background region not including the subject in the image from the image; compressing the background removed image; transmitting the background removed image compressed via a network; receiving the background removed image compressed via the network; decoding the background removed image compressed and received; generating a restored image by synthesizing the background removed image decoded and the background image; and comparing the restored image with the background image to extract the subject.

The invention provides an accelerator determination method based on a field-programmable gate array, an image processing method, equipment and a storage medium, which can be applied to the technical field of image compression. The accelerator determination method based on the field programmable gate array comprises the steps that a fusion factor list is determined according to the number of fusion units corresponding to a network model, the fusion factor list comprises a plurality of fusion factors, and the fusion factors represent the number of the fusion units needed for fusing the fusion units in the network model into a fusion structure; under the storage constraint and bandwidth constraint of the field programmable gate array, determining a target fusion factor from the plurality of fusion factors according to the image data block parameters and the fusion network parameter sets respectively corresponding to the plurality of fusion factors; and according to the target fusion factor and the fusion network parameter set corresponding to the target fusion factor, performing parameter mapping on the field programmable gate array to obtain an accelerator for realizing image compression.