176 results about "Adaptive resolution" patented technology

The invention relates to the technical field of data processing, and discloses a multi-modal digital human generation method and system based on AIGC and a storage medium. The method comprises the steps of performing modeling and dynamic weight adjustment processing on multi-modal feature data to obtain dynamic personalized knowledge data; performing intelligent matching processing on the target scene information and the dynamic personalized knowledge data to obtain situational behavior instruction data; performing hierarchical action sequence generation, adaptive resolution optimization and speech synthesis processing on the initial digital human to obtain multi-modal digital human performance data; and behavior deviation identification is carried out on the multi-modal digital human performance data to obtain behavior deviation data and performance feedback data, and adaptive optimization processing is carried out on the multi-modal digital human performance data and the performance feedback data to obtain a target digital human. According to the invention, the efficiency and accuracy of multi-modal digital human generation based on AIGC are improved.

The invention provides a rail transit video intelligent analysis method, medium and system, and belongs to the technical field of rail transit, and the method comprises the steps: constructing a self-adaptive resolution image hierarchical structure, and dynamically determining an optimal resolution hierarchy based on a minimum spanning tree algorithm; constructing an abnormal target movement matrix by combining an improved frame difference method with an optical flow estimation technology; applying a Hungary algorithm to realize target tracking; constructing an abnormal target change index to evaluate a behavior abnormal degree; dividing monitoring stages according to the running state of the vehicle to realize scene self-adaption; an orbit scene attention network model is introduced to identify abnormal behaviors; quantifying a risk level through an abnormal behavior risk assessment function; implementing a hierarchical processing strategy to enable a low-resolution hierarchy to be responsible for global rapid screening and a high-resolution hierarchy to be responsible for fine analysis of key areas; the risk trend is estimated in combination with the rail transit abnormal event prediction model, and the technical problems of large calculation amount and low efficiency of high-definition video processing are effectively solved.

The invention discloses a low-altitude path planning method and system based on a dynamic adaptive graph neural network, and belongs to the technical field of artificial intelligence and robot autonomous navigation. Aiming at the problems of large calculation amount of a fixed grid map, slow dynamic response of a static octree, failure of a traditional heuristic function on a non-uniform graph and the like, the invention provides the following scheme: constructing a resolution self-adaptive non-uniform graph by using the octree; a Morton code is adopted to realize rapid positioning of a dynamic obstacle and millisecond-level updating of a map; an attention mechanism is introduced into a graph attention network (GAT), weights are adaptively allocated to different neighbor nodes, features are aggregated, and a high-precision heuristic cost estimation value is output; and finally, integrating the estimated value into an algorithm to perform efficient path search. According to the method, the memory occupation and the calculation complexity are remarkably reduced, and the planning efficiency and the path safety in a dynamic environment are improved.

The invention discloses a hydrocyclone flow field simulation method based on an adaptive smoothed particle method, and the simulation method comprises the following steps: (1) determining structural parameters of a hydrocyclone, and constructing a geometric model of the hydrocyclone; (2) establishing a basic control equation, and discretizing the basic control equation into an adaptive smoothed particle normal equation; (3) setting boundary conditions and initial calculation parameters on the basis of the geometric model of the hydrocyclone, and then importing the boundary conditions and the initial calculation parameters into a fluid simulation scene for simulation; and (4) respectively monitoring the particle flow at the outlet of the underflow pipe of the hydrocyclone and the flow at the outlet of the overflow pipe, and stopping calculation after the flows at the two outlets are stable, thereby completing simulation. The flow field behavior in the hydrocyclone is simulated through the adaptive resolution smoothed particle method, the change and breakage of the interface in the hydrocyclone can be accurately captured, it is guaranteed that the change at the gas-liquid interface is clear and visible, the track of particles in the hydrocyclone is traceable, and the calculation amount and the calculation time are reduced through the adaptive resolution.

The invention discloses an ambiguity adaptive resolving method and system based on ILS and BIE estimation. The method comprises the following steps: acquiring GNSS original observed quantity; constructing a pseudo-range and carrier phase double-difference observation equation, and calculating a floating point solution of an ambiguity parameter by using extended Kalman filtering; performing ambiguity fixation on the ambiguity subset through an ILS algorithm to obtain an ILS fixed solution, performing ambiguity fixed check on the ILS fixed solution, if the check is passed, obtaining a final solution, and if the check is not passed, performing ambiguity fixation through a BIE algorithm to obtain a BIE fixed solution: performing multiple screening on the ambiguity subset based on an observation value domain and a state domain to obtain an optimal ambiguity subset; searching the optimal ambiguity subset by using an improved SEVB algorithm to obtain a BIE multi-ambiguity candidate solution; and calculating a BIE fixed solution, and performing reliability verification on the BIE fixed solution to obtain a final fixed solution. According to the method, the ambiguity fixing success rate can be improved, meanwhile, the precision of a fixed solution is remarkably improved, and the ambiguity resolving efficiency is effectively optimized.

The invention provides a self-adaptive multi-resolution power system simulation method and device based on physical information, and relates to the technical field of power system simulation. The method comprises the following steps: acquiring model data and operation state data of a power system; constructing a simulation system corresponding to the power system based on the model data, the operation state data and the multi-level resolution model library; determining a target model resolution corresponding to each subsystem through a self-adaptive resolution control strategy and a multi-level resolution model library; and distributing the target model resolution to the corresponding subsystem, and performing simulation calculation on the subsystem of the simulation system based on the multi-level resolution model library and the adaptive resolution control strategy to obtain a simulation calculation result corresponding to the power system. According to the embodiment of the invention, by designing the adaptive resolution control strategy, the dynamic adjustment of the resolution of different regional models of the power system is realized, and the calculation efficiency can be greatly improved while the simulation precision is maintained.

The invention provides an image processing method and system applied to a display area of a virtual exhibition hall. The method comprises the following steps: collecting viewing distance data and view angle deviation angle data; generating a dynamic sensing result according to the data; determining a resolution threshold range based on the dynamic sensing result; if the resolution threshold range exceeds a preset standard value, generating an adaptive resolution image; when it is detected that the focus area coordinates are displaced, fast Fourier transform is executed on the self-adaptive resolution image, and a frequency domain focus image is obtained; optimizing the frequency domain focus image to generate an optimized focus detail image; generating display frame data based on the focus detail image; and inputting the display frame data into a user behavior analysis and prediction module, and obtaining pre-loaded display content during network delay. The definition of the displayed content is automatically adjusted, related content can be cached in advance according to the browsing track and interest preference of the user, and waiting time is shortened.

This disclosure relates to signaling, parsing, and using adaptive resolution for motion vector difference in video coding. An example method includes receiving a video bitstream and extracting an inter-prediction syntax element from the video bitstream. The inter-prediction syntax element indicates which single-reference inter-prediction mode is enabled for one or more video blocks of the video bitstream. The method further includes determining whether an adaptive motion vector difference (MVD) mode is enabled for the one or more video blocks. The adaptive MVD mode is a single-reference inter-prediction mode with an adaptive MVD pixel resolution. When the adaptive MVD mode is enabled for the one or more video blocks, the method includes selecting a current MVD pixel resolution from a set of available MVD pixel resolutions. The method also includes decoding the one or more video blocks based on the current MVD pixel resolution.

The invention discloses a carbon footprint monitoring system suitable for a high altitude area and an energy-saving data processing method, and the method comprises the steps: firstly, through an EnKF (Ensemble Kalman Filter) technology, fusing multi-source heterogeneous data such as satellite remote sensing and ground monitoring according to a data source reliability "matching", and overcoming the data sparsity; secondly, based on the oxygen partial pressure corresponding to the local altitude and the'ratio 'of a key sensitivity coefficient # imgabs0 #, applying a specific correction function to dynamically adjust an emission factor; and finally, downscaling the coarse-resolution carbon emission data by adopting an adaptive-resolution convolutional neural network to generate a high-precision and high-resolution carbon emission spatial distribution diagram.

The invention provides an SLAM (Simultaneous Localization and Mapping) optimization method and equipment based on point cloud registration and adaptive resolution, and a medium, and relates to the technical field of AGV (Automatic Guided Vehicle) positioning and mapping, and the method comprises the following steps: (1) inputting and preprocessing sensor data; (2) front-end scanning and matching: based on the preprocessed data, carrying out point cloud registration through a GICP algorithm, updating the pose of the current frame and constructing a local subgraph; (3) global SLAM: receiving sensor data, poses and subgraph data from the front-end scanning and matching step, and carrying out loopback detection and global optimization; wherein a self-adaptive resolution switching strategy based on environment complexity is adopted in the loopback detection process; according to the GICP algorithm, the surface of the point cloud is modeled as Gaussian distribution, local features are described through a covariance matrix, and a target error function constructed based on the mahalanobis distance is optimized to estimate pose transformation. According to the method, the local matching precision and robustness are improved by replacing ICP with GICP, and the global calculation efficiency is adjusted and optimized in combination with the dynamic resolution.

The embodiment of the invention discloses a screen projection method and device, a terminal and a storage medium, and relates to the technical field of screen projection. Comprising the steps of determining a target adaptive resolution from at least two adaptive resolutions supported by an application program based on an expected resolution of a destination end under the condition that a screen projection demand exists; determining a virtual screen resolution of a virtual screen based on the target adaptive resolution, wherein the aspect ratio of the virtual screen resolution is consistent with the aspect ratio of the target adaptive resolution; based on the virtual screen resolution, the source end coding resolution and the expected resolution, determining a target coding resolution, the source end coding resolution being related to the coding capability of the source end; performing video coding on the application picture by using a coder with a target coding resolution to obtain a screen projection data stream; and transmitting the screen projection data stream to the destination end, so that the destination end performs screen projection display based on the screen projection data stream. According to the scheme, black edges appearing when the target end displays the screen projection picture can be reduced.

The invention relates to a high-fidelity generative video stream transmission system based on a visual base model, which belongs to the field of image communication, and is characterized in that a visual enhancement-oriented generative codec is designed, and high-fidelity video reconstruction under a high compression ratio is realized through an asymmetric space-time compression strategy and time sequence consistency enhancement; a resolution scaling module is provided, the calculation complexity is remarkably reduced through a video super-resolution recovery module of adaptive resolution control and joint optimization, and real-time high-definition video processing is achieved; and constructing a network adaptive video stream transmission controller, an intelligent token discarding mechanism based on semantic importance and a mixed packet loss processing strategy to realize code rate scalable control and robust transmission under network fluctuation.

A video encoder includes circuitry to generate an encoded bitstream for decoding by a compliant decoder, the encoded bitstream including a first picture to be used as a reference picture, a current picture comprising a first coded block and a second coded block, a signal indicating that a block-based mode when a reference picture and a current picture have different resolutions is enabled, and information including an index useful for determining a scaling constant. The compliant decoder has circuitry configured to receive the bitstream; determine whether the block-based mode is enabled, and if enabled utilizing the mode to reconstruct the first block and reconstruct the second block without using the mode.

An example method of video decoding includes receiving a video bitstream that includes a plurality of encoded blocks including a current block. The example includes determining that the current block is inter-coded using a prediction block and a motion vector (MV). When an adaptive motion vector difference (AMVD) resolution mode is active for the current block, a reference motion vector (RMV) index is determined for a dynamic reference list (DRL), where the RMV index for the DRL has a first range when the AMVD resolution mode is active. When the AMVD resolution mode is inactive for the current block, the RMV index for the DRL is extracted from the video bitstream, where the RMV index for the DRL has a second range, greater than the first range.

This disclosure relates generally to video coding and particularly to methods and systems for providing schemes for setting allowable motion vector different values when implementing adaptive resolution for motion vector difference. An example method for processing a current video block of a video stream is disclosed. The method may include receiving the video stream; determining that the current video block is inter-coded based on a prediction block and a motion vector (MV), wherein the MV is to be derived from a reference motion vector (RMV) and a motion vector difference (MVD) for the current video block. The method further include in response to determining that the MVD is coded with an adaptive MVD pixel resolution: determining a reference MVD pixel precision for the current video block; identifying a maximum allowed MVD pixel precision; determining a set of allowable MVD levels for the current video block based on the reference MVD pixel precision and the maximum allowed MVD pixel precision; and deriving the MVD from the video stream according to at least one MVD parameters signaled in the video stream for the current video block and the set of allowable MVD levels.

The invention belongs to pattern recognition and artificial intelligence, and particularly provides a multi-modal large language model optimization method and system based on adaptive resolution, and the method comprises the steps: dividing multi-modal question and answer data into a target task training set and a target task test set; constructing a resolution selection training set by using the recollected image data in the target scene and the paired text instruction; constructing a multi-modal large language model with a two-stage image coding mechanism, and training the multi-modal large language model by using the target task training set and the resolution selection training set to obtain a target model; the prediction accuracy of the target model is evaluated on the target task test set, and optimization of the multi-modal large language model is completed. According to the technical scheme, the optimal resolution is adaptively selected for reasoning through a two-stage image coding mechanism, so that the visual perception capability of the model is remarkably improved.

The invention discloses a robot fine operation control system based on a diffusion model and 3D vision, particularly relates to the technical field of industrial robot fine operation control, and aims to solve the problem that when an existing industrial robot executes fine operations such as bottle cap screwing and connector plugging in and out in a complex three-dimensional operation scene, the operation efficiency is high. The problems that three-dimensional perception is unstable, the action resolution is fixed, space and contact constraints are difficult to meet, and the task success rate and safety are insufficient are solved. The method comprises the following steps: constructing a voxel feature field updated along with time under a self-body coordinate system, generating interaction complexity and a physical constraint field based on task coding, and linking adaptive resolution and action granularity scheduling, diffusion trajectory generation and closed-loop execution correction to uniformly map environmental geometry, contact conditions and task stages into tail end trajectory control, so as to realize real-time tracking control. Therefore, fine operations such as bottle cap screwing, connector inserting and pulling and flexible object folding can still be stably completed under complex shielding and contact constraint, and the effects of safety and task success rate are both considered.

A railway roadbed disease diagnosis method based on a convolutional neural network comprises the following steps: acquiring vibration acceleration signals of a train and a railway roadbed, and performing data cleaning on the acquired vibration signals; signal preprocessing, time-frequency domain transformation and feature vector extraction, convolutional neural network-based model training and feature extraction, feature classification and disease recognition, and real-time disease detection and location positioning are realized. According to the invention, a modern signal processing technology and a deep learning algorithm are combined to realize efficient and automatic detection of railway roadbed diseases; signal segmentation, time-frequency domain analysis, image segmentation and convolutional neural network technologies are adopted, a self-adaptive resolution adjustment mechanism is achieved, accuracy and high efficiency of signal feature capture and disease diagnosis are achieved, and the nonlinear distortion problem of multi-band signals can be effectively solved through signal segmentation processing and summarizing fusion.

The invention discloses a two-stage self-adaptive complex terrain global path planning method, which comprises the following steps of: calculating movement cost by taking a grid unit corresponding to the finest resolution as a unit and fusing gradient, ground cover, roughness and topographic relief; determining the passing cost of the region; a path planned in the first stage is used as a reference path of the second stage, the problems of efficiency and precision of the second path planning stage are comprehensively considered, an adaptive resolution mechanism is adopted, and adaptive path end point judgment is adopted for each middle section of path in the second stage, so that the flexibility and expandability of the path are enhanced, and the path planning efficiency is improved. And accurate and rapid path planning of a complex terrain path is realized.

A mechanism is described for facilitating adaptive resolution and viewpoint-prediction for immersive media in computing environments. An apparatus of embodiments, as described herein, includes one or more processors to receive viewing positions associated with a user with respect to a display, and analyze relevance of media contents based on the viewing positions, where the media content includes immersive videos of scenes captured by one or more cameras. The one or more processors are further to predict portions of the media contents as relevant portions based on the viewing positions and transmit the relevant portions to be rendered and displayed.

The invention relates to the technical field of Internet of Things and multimedia communication, in particular to a multimedia equipment centralized control method based on the Internet of Things, which comprises the following steps: realizing heterogeneous equipment access through a gateway dynamic analysis protocol of the Internet of Things; collecting multi-source data by utilizing an edge computing node, and detecting anomaly through Kalman filtering fusion and an isolated forest model; a dynamic control strategy is generated based on an LSTM neural network and a scene rule base, and synchronous switching of audio and video streams and self-adaptive adjustment of resolution are realized; control delay is guaranteed through hierarchical caching and a time-sensitive network protocol stack; and multi-terminal control is supported, and hierarchical authority management is implemented through a role authority matrix. According to the invention, the problems of difficult compatibility, insufficient control real-time performance and extensive safety management of heterogeneous equipment are solved, and the cooperation efficiency, response speed and use safety of multimedia equipment are effectively improved.

An X-ray detector comprises a detector panel (100) comprising a surface with a plurality of detector pixels, wherein the detector pixels are configured to convert received X-rays into electric signals representative of values indicative of the received X-rays. A data interface (308) transmits images having a fixed number of output pixels. A control unit controls to set (401) a region of interest comprising at least a subset of the plurality of detector pixels, wherein a number of detector pixels in the region of interest is independent of the number of output pixels. The control unit maps (403) the region of interest onto an output image having the fixed number of output pixels. The control unit resamples (404) the detector pixels within the region of interest to obtain values for the output pixels of the output image, and transmits (405) the output image via the data interface.

An encoder configured to encode a video bitstream for decoding by a compliant decoder configured to receive the bitstream, the encoded bitstream including a reference picture and a current picture including a coded current block, the bitstream also including an index useful for determining a scaling factor. The decoder determines that a mode when a reference picture and a current picture have different resolutions is enabled. Utilizing the mode, the decoder reconstructs the coded current block encoded by the encoder by determining a scaling factor using information in the bitstream including the index, determining a scaled prediction block by scaling a block of the reference picture using the scaling factor and by applying a pixel interpolation filter determined specifically for the prediction block and combining the scaled prediction block with a residual.

The invention discloses an adaptive vertical resolution enhancement method based on a digital oscilloscope, and the method comprises the steps: constructing a coefficient table composed of different types of prototype low-pass filter coefficients and corresponding different enhancement resolution digits and index values through designing different types of low-pass filter time domain coefficients; then sampling input data in real time, estimating an index value and a frequency shift point number of a resolution enhancement digit corresponding to a sampling signal through a library function in an upper computer, calling a corresponding prototype low-pass filter coefficient from a coefficient table according to the index value, issuing the prototype low-pass filter coefficient to the FPGA, and then generating a target band-pass filter in the FPGA by combining the frequency shift point number; and finally, performing frequency domain filtering to obtain an output signal after adaptive resolution enhancement so as to realize resolution enhancement.

A method includes receiving a reference frame, determining a scaling constant for a current block, determining a scaled reference block using the reference frame and the scaling constant, determining a scaled prediction block using the scaled reference block, and reconstructing pixel data of the current block using the scaled prediction block. Related apparatus, systems, techniques, and articles are also described.

The invention relates to the technical field of electrical digital data processing, and discloses an intelligent LED display screen connection method, which comprises the following steps of: installing an LED box body, dynamically generating a box body connection topological graph according to position information and resolution parameters of the LED box body, generating display data through a self-adaptive resolution matching algorithm, and displaying the display data in the box body connection topological graph. The display image is previewed and changed through a visualization method, the data integrity is verified through a redundancy check mechanism, and the LED boxes display the image content cooperatively. According to the method, the traditional screen connection mode of the LED display screen is improved, the automation degree is improved, the early-stage labor cost is reduced, and the screen connection efficiency and the display quality of the LED display screen are remarkably improved.

This disclosure signaling of motion vector or motion vector difference dependent on whether magnitude-dependent adaptive motion vector difference pixel resolution is employed or not in video encoding and decoding. An example method for processing a video block of a video stream is disclosed. The method may include receiving the video stream; determining that the video block is inter-coded based on a prediction block and a motion vector (MV), wherein the MV is to be derived from a reference motion vector (RMV) and a motion vector difference (MVD) for the video block; extracting or deriving, from the video stream, a data item associated with at least one of the RMV or the MVD.

A method, device, and non-transitory computer-readable medium for decoding an encoded video bitstream using at least one processor, including, obtaining from the encoded video bitstream a first flag indicating that reference picture resampling is enabled for coded video sequence (CVS); determining a value of a second flag indicating whether a picture resolution is changed in the CVS; based on the value of the second flag indicating that the picture resolution is changed in the CVS, decoding the CVS using the reference picture resampling for spatial scalability and adaptive resolution change (ARC); and based on the value of the second flag indicating that the picture resolution is not changed in the CVS, decoding the CVS using the reference picture resampling for the spatial scalability, and without using the reference picture resampling for the ARC.

A video encoder generates an encoded bitstream which includes a reference picture, a current picture having a resolution different from the reference picture and also including a first block, an intra-coded second block, and information useful for determining a scaling constant. The encoded bitstream is decodable by a video decoder receiving the encoded bitstream and determining whether a block-based mode for decoding a current picture of one resolution using a reference picture of a different resolution is enabled. When enabled, the decoder uses the mode to decode the first block and decodes the intra-coded second block without using the mode.

A video decoding apparatus and a method for adaptively setting a resolution are disclosed. According to one embodiment of the present invention, a method for adaptively setting a resolution on a per-picture basis comprises the steps of: decoding maximum resolution information from a bitstream; decoding, from the bitstream, resolution information about a current picture; and setting the resolution of the current picture on the basis of the maximum resolution information or the resolution information, wherein the resolution information has a size less than or equal to that of the maximum resolution information.