875 results about "Video decoding" patented technology

The invention relates to the technical field of image processing, and further relates to a video decoding and unreal engine rendering method based on GPU full-link zero copy, which comprises the following steps of: 1, performing hardware decoding on an input video code stream on a GPU, and constructing a motion vector description buffer region for storing compressed domain motion vector information according to a macro block sequence; step 2, reading the motion vector description buffer area on the GPU through a calculation shader, and generating dynamic special effect control buffer areas in one-to-one correspondence with the macro blocks; and step 3, in a post-processing material of the unreal engine rendering module, taking the shared video texture resource as an input texture, and outputting a video picture. On the premise of not depending on a host processor and not excessively occupying video memory bandwidth, unified management of pixel data and motion data is achieved, delay is remarkably reduced, and special effect stability and direction consistency are improved.

A video decoding method includes: determining first motion information of a current block; refining the first motion information based on motion information of a reference picture of the current block to obtain second motion information of the current block; and determining a prediction value of the current block based on the second motion information.

The invention provides a cross-platform video decoding method and device, computing equipment and a computer readable storage medium, and the method is combined with a factory mode to completely package bottom layer differences of all platform types, and an application layer developer does not need to care about the bottom layer platform differences. The optimal implementation can be automatically selected on different engines and platforms through a uniform API (Application Program Interface); during rendering, a single-frame memory management strategy is used, and only one frame which is currently displayed is reserved in a memory; and in the aspect of performance, the advantages of a multi-thread platform and the parallel computing characteristics of the GPU are fully utilized. According to the embodiment of the invention, through deep fusion of a cross-platform soft decoding architecture, single-frame memory optimization, multi-thread parallel, GPU acceleration and other technologies, perfect balance of cross-platform, high performance and low memory is realized, and the development efficiency of the whole project is improved.

Provided are an image decoding method and an image decoding apparatus, and an image encoding method and an image encoding apparatus which correspond thereto, the image decoding method including: selecting a current block from among a plurality of blocks obtained by dividing a current image; determining a plurality of transform blocks including a first transform block and a second transform block based on the current block; scaling a first direct current (DC) transform coefficient value of the first transform block using a size of the first transform block and a reference transform size to obtain a scaled first DC transform coefficient value; obtaining a prediction transform coefficient value for the second transform block based on a size of the second transform block and the scaled first DC transform coefficient value; determining a second DC transform coefficient value of the second transform block based on the prediction transform coefficient value; and restoring the current block by performing an inverse transform on the second transform block based on the second DC transform coefficient value

The invention discloses an RTSP video stream AI processing method and system based on a tsn network, which realize end-to-end deterministic transmission and processing, guarantee low-delay and low-jitter transmission of a video stream from a source to an AI unit through a TSN, meet the industrial-grade real-time requirement and perform efficient edge AI processing. The problem that a traditional CPU is low in efficiency or a GPU is high in power consumption is solved, real-time analysis of the high energy efficiency ratio and high system integration are achieved, network transmission, video decoding, AI reasoning and result visualization are integrated into a single embedded platform, and hardware complexity and cost are reduced.

Provided are a video encoding method, a video decoding method, and a bitstream generating method using an identifier indicating whether a corresponding chroma component is filtered by an adaptive loop filter (ALF).SOLUTION: The video encoding method includes encoding an image to generate a bitstream. In the bitstream, a first syntax element is configured to indicate whether the first chromaticity component is filtered with an adaptive loop filter (ALF), and a second syntax element is configured to indicate whether the second chromaticity component is filtered with the ALF.SELECTED DRAWING: Figure 5

A video encoding and decoding method and apparatus for training models with quantization constraint optimization. The method obtains training video frames and extracts feature maps using a video encoding and decoding model. Scale parameter values are determined for each feature element and mapped to obtain scale parameter mapping values within a preset range. Constraint reference mapping values are obtained with distances to rounding boundary values greater than corresponding scale parameter mapping values. A quantization constraint loss is determined based on differences between scale parameter mapping values and constraint reference mapping values. Model parameters are updated using this quantization constraint loss to obtain a trained video encoding and decoding model with improved quantization performance and compression efficiency.

To provide a method and apparatus for improving image coding efficiency.SOLUTION: An image decoding method includes the steps of: acquiring a sign data hiding enable flag; acquiring a transform skip residual coding (TSRC) enable flag based on the sign data hiding enable flag; acquiring residual information for a current block based on the TSRC enable flag; deriving a residual sample of the current block based on the residual information; and generating a reconstructed picture based on the residual sample. The sign data hiding enable flag is a flag indicating whether sign data hiding is enabled, the TSRC enable flag is a flag indicating whether TSRC is enabled, and the TSRC enable flag is acquired based on the sign data hiding enable flag having a value of zero.SELECTED DRAWING: Figure 10

The invention provides a long video understanding method and system based on sparse sampling in the technical field of computer vision, and the method comprises the steps: S1, dividing each long video, decoding each sub-video into frames, and carrying out the uniform sampling of each frame; s2, extracting global features of each long video, fragment-level features of the sub-videos and frame-level features of the frames, and constructing a multi-granularity video database based on each sub-video, the global features, the fragment-level features and the frame-level features; s3, analyzing the long video query request to obtain a target object and a clue object; s4, the planning decision Agent plans a retrieval strategy based on the target object and the clue object; s5, the interactive Agent performs retrieval operation on the multi-granularity video database based on the retrieval strategy; and S6, verifying the retrieval result to obtain a verification result, and iterating the retrieval strategy based on the verification result, or outputting the retrieval result. The method has the advantage that the accuracy and efficiency of long video understanding are greatly improved.

A method and an apparatus are disclosed for video coding CC-ALF based on a nonlinear cross-component relation. A video decoding device obtains a reconstructed frame that is an output of a sample adaptive offset (SAO) filter and generates an adaptive loop filter output (ALF output) by inputting the reconstructed frame into an adaptive loop filter (ALF). The ALF output includes a luma ALF output and a chroma ALF output. The video decoding device generates corrected values of a chroma component by inputting the luma ALF output into a nonlinear cross-component ALF (nonlinear CC-ALF) and generates an enhanced chroma ALF output by summing the corrected values of the chroma component and the chroma ALF output.

A device for decoding video data includes an integrated circuit (IC) comprising a video decoder, and a memory that is external to the IC and coupled to the IC. The video decoder is configured to in a first mode, decode a first frame based on a first reference frame stored in the memory, and in a second mode, decode a second frame based on a second lossy reference frame, wherein the second lossy reference frame is generated based on decompression of a lossy compressed reference frame.

Some aspects of the disclosure provide a method of video decoding. In some examples, values of one or more target quantization coefficients in a target region of quantization coefficients of a current block are obtained. A sub-block transform (SBT) mode of the current block is derived based on the values of the one or more target quantization coefficients in the target region. The current block is reconstructed based on the SBT mode of the current block. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

The invention relates to the technical field of wind power plant AGC (Automatic Gain Control) systems, and discloses a video decoding and model fusion-based AGC system reliability early warning system, which is characterized in that monitoring equipment is accessed through a bypass of a video acquisition security access module, and an interface video stream is captured in real time; a video analysis feature extraction module synchronously decodes and extracts visual state features and multi-source data features; the intelligent diagnosis reasoning module independently diagnoses a system dead state based on visual features, and verifies information consistency and a locking state through a logic knowledge base based on multi-source data. And finally, the dual effects of realizing reliable external detection on a dead halt state with complete internal monitoring failure and realizing deep intelligent diagnosis on multi-source information logic conflicts are achieved, and the problems of blind area and shallow alarm of traditional monitoring are solved.

Methods for video decoding and encoding, apparatuses and non-transitory computer-readable storage media thereof are provided. In one method for video decoding, a decoder may obtain a first and a second block, where the first block is coded with an Intra Block Copy (IBC) mode or an intra Template Matching Prediction (TMP) mode, and the second block is coded with the intra TMP mode or the IBC mode. Additionally, the decoder may obtain a boundary strength for a deblocking filter by applying a predefined criterion in one of an intra mode or an inter mode. Further, the decoder may apply, and based on the boundary strength, the deblocking filter on the first block and the second block.

The present disclosure provides video encoding and decoding methods, which include: determining a prediction mode of the current block; determining a reference block of the current block, and determining N groups of linear model parameters, N being a positive integer greater than 1; selecting a target group of linear model parameters from the N groups of linear model parameters, and determining a prediction block of the current block according to the target group of linear model parameters.

A video encoding / decoding method and a video encoding / decoding apparatus are provided. A video decoding method comprises generating an intra prediction mode list based on intra prediction modes of neighboring blocks adjacent to a current block. The video decoding method further comprises selecting at least three intra prediction modes from the intra prediction mode list based on a number of intra prediction modes occurring in the intra prediction mode list being three or more. The video decoding method further comprises generating at least three prediction blocks based on the at least three intra prediction modes. The video decoding method further comprises generating a prediction block of the current block by performing weighted averaging on the at least three prediction blocks.

Embodiments of the present disclosure provide a method, an apparatus, an electronic device, a computer-readable storage medium, a computer program product, and a computer program for video decoding. The method obtains playback address information of a video to be played, the playback address information carrying encoding format information of the video to be played; obtains the video to be played in accordance with the playback address information; and, in progress of obtaining the video to be played asynchronously, acquires a hardware decoder based on the encoding format information of the video to be played; and decodes the obtained video to be played with the hardware decoder. Embodiments of the present disclosure carry the encoding format information of the video to be played in the playback address information of the video, so that the asynchronous acquisition of the hardware decoder can be adopted in progress of the startup of video playback.

This invention discloses an end-to-end examination behavior analysis method and system, comprising a video input management module, a video decoding module, an image preprocessing module, a raw frame prediction queue, a raw frame queue, an AI module, an analysis result recording module, and an abnormal event video generation module. It utilizes an end-to-end AI model training and inference scheme, enabling efficient training using large amounts of historical data. In practice, it offers fast processing speed and high efficiency. The end-to-end AI model takes continuous video frames as input and outputs bounding boxes indicating suspected violations after inference. In the post-processing section, the model output undergoes spatiotemporal correlation and filtering to finally generate spatiotemporal location information of suspected violations. It exhibits good scene adaptability; when new scenes are needed or new actions to be identified are added, only new training data needs to be added and retrained to expand the algorithm, saving manpower and improving efficiency.

Methods for video decoding and encoding, apparatuses, and non-transitory computer-readable storage media are provided. In one method, a decoder may obtain a first block vector (BV) and a second BV based on a bi-predicted intra block copy (IBC) mode. Additionally, the decoder may generate a first prediction block based on the first BV and generating, by the decoder, a second prediction block based on the second BV. Furthermore, the decoder may obtain a final prediction block for a current block based on the first prediction block and the second prediction block.

A video decoding method according to an embodiment comprises: obtaining flag information indicating whether MIP is applied and prediction mode information of a current block; when the flag information indicates that MIP is applied and a prediction mode of the current block is an MIP prediction mode, setting a reference region used for MIP on the basis of condition information of the current block; determining a matrix used for MIP; and obtaining a prediction sample of the current block on the basis of the reference region and the matrix.

To provide a method and apparatus for increasing video coding efficiency.SOLUTION: The video decoding method according to the present document includes deriving an intra prediction mode of a chroma block as a cross-componentlinearmodel (CCLM) mode based on intra prediction mode information, updating the intra prediction mode of the chroma block based on an intra prediction mode of a luma block corresponding to the chroma block, remapping the updated intra prediction mode to a wide-angle intra prediction mode when the chroma block is not a square, and determining an LFNST set including an LFNST matrix based on the remapped intra prediction mode.SELECTED DRAWING: Figure 16

A method of video decoding, comprising: obtaining a bitstream comprising a plurality of coded frames in a video signal; decoding the plurality of coded frames into a plurality of superblocks and decoding the plurality of superblocks into a plurality of residual blocks; recovering each of the plurality of residual blocks into a coded block based on a multi-reference line intra prediction flag and reference samples in each coded frame, wherein a plurality of reference lines are divided into an upper reference line and a left reference column, and one upper reference line and one left reference column are selected for intra prediction; reconstructing each frame in the video signal by storing the recovered coded block of each of the plurality of residual blocks in a frame buffer; and outputting the reconstructed frames in succession to recover the video signal.

The invention discloses a video coding method and device and a video decoding method and device based on residual prediction, and is applied to the technical field of video processing. The coding method comprises the following steps: determining a motion vector and a disparity vector of a current coding block; determining a first parallax compensation block corresponding to the current coding block in the reference view according to the parallax vector; determining a prediction residual according to the current coding block, the first parallax compensation block, and the motion vector and the parallax vector of the first parallax compensation block; or determining a first time domain motion compensation block corresponding to the current coding block in the previous frame and / or the next frame of image of the current coding block according to the motion vector; determining a prediction residual according to the current coding block, the first time domain motion compensation block, and the motion vector and the disparity vector of the current coding block; and coding the current coding block according to the prediction residual error. According to the method, the accuracy of the obtained prediction residual error can be improved, so that the coding compression efficiency and the coding effect of the multi-view video are improved.

A video decoding method and device according to the present disclosure may receive a bitstream including an encoded video picture and reconstruct the encoded video picture included in the bitstream. Here, the bitstream may include a quality metric SEI message. The quality metric SEI message may include a quality metric definition flag indicating whether information defining the quality metrics is included in the quality metric SEI message, and quality metric number information indicating the number of quality metric entries included in the quality metric SEI message.

A method and an apparatus are disclosed for video coding for deriving intra-prediction modes based on a reference pixel. In the disclosed embodiments, a video decoding device generates sub-pixel reference lines from integer-pixel reference lines. The video decoding device derives an implicit prediction mode by using the sub-pixel reference lines. Information for the implicit prediction mode includes a prediction direction and an upward prediction mode flag that indicates whether the prediction direction is upward. The video decoding device generates an intra-predictor of the current block by using the integer-pixel reference lines and the implicit prediction mode.

Methods, apparatus, and non-transitory computer-readable storage media for video decoding and encoding are provided. In a method for video decoding, a decoder may: determine a non-adjacent neighboring block of a current inter-coded block, where the non-adjacent neighboring block includes a plurality of reconstruction sample points that are non-adjacent to the current inter-coded block; obtaining a plurality of prediction sample points of the non-adjacent adjacent blocks based on the motion vectors of the non-adjacent adjacent blocks; obtaining a filter based on the plurality of prediction sample points and the plurality of reconstruction sample points; obtaining a current prediction block based on the motion vector of the current inter-frame coding block; and obtaining a filtered prediction block based on the filter and the current prediction block.

Systems, methods, and instrumentalities are configured for intra template matching prediction fusion. In examples, a video decoding device may be configured to determine that intra template matching prediction (ITMP) fusion is used for a video block. The device may obtain a selected block vector (BV) indication configured to indicate a selected BV candidate. The device may determine, based on the selected BV candidate, a set of BV candidates for fusion. The device may reconstruct the video block based on the determined set of BV candidates.

In order to suppress an increase in the amount of processing required for pre-processing or post-processing in a video coding scheme that uses pre-processing and post-processing, this video coding device includes: a first acquisition means for acquiring first coordinates indicating the position of a partial region of a picture; a second acquisition means for acquiring second coordinates by processing the first coordinates to make the coordinate values even numbers; a third acquisition means for acquiring third coordinates on the basis of the partial region represented by the second coordinates; and a correction means for processing the third coordinates to make the coordinate values even numbers.

A video decoding method including: determining whether to apply split prediction for a current coding unit; based on the split prediction being applied to the current coding unit, determining a neighboring area of the current coding unit; predicting a split scheme for the current coding unit using split-associated information obtained from the neighboring area; based on the split scheme indicating a split of the current coding unit, obtaining at least one lower coding unit by splitting the current coding unit according to the split scheme; and based on the split scheme indicating no split of the current coding unit, decoding the current coding unit, wherein the neighboring area is included in a current picture including the current coding unit, or included in a picture decoded before the current picture.

The present application discloses a video decoding method, a video encoding method, a storage medium, an electronic device and a product. The video decoding method comprises: obtaining a video bitstream, wherein the video bitstream comprises decoding indication information, and the decoding indication information comprises at least one filter flag bit used for indicating a filter parameter; on the basis of a value of the filter flag bit, determining tap coefficient information in the filter parameter; and on the basis of the tap coefficient information, determining the filter parameter.