118results about "Video signal spatial resolution conversion" patented technology

The invention relates to the technical field of digital twinning, particularly provides a digital twinning scene adaptive optimization method based on point cloud data, and solves the problems that smoothness and detail presentation cannot be balanced during network fluctuation, and a scene prediction optimization mechanism based on space-time semantic analysis is not established. The method comprises the following steps: data preprocessing and hierarchical construction: carrying out preprocessing of abnormal point elimination, missing value complementation and density adjustment on original point cloud data, dividing key and common regions according to scene requirements, and constructing a multi-scale and multi-resolution hierarchical point cloud data system; the method can deeply analyze the spatio-temporal dynamic characteristics of the point cloud data through the technologies of spatio-temporal dynamic semantic segmentation, dynamic change monitoring, prediction optimization and the like, processes the continuous time sequence point cloud data after adaptive transmission, models a time dependency relationship and extracts local and global characteristics in time and space dimensions respectively, and improves the accuracy of point cloud data processing. Accurate identification of object types, positions and dynamic change information is realized.

Disclosed herein is zero-latency switching between two resolution and frame rate modes. The system includes receiving a trigger to switch a video data stream of frames between a first resolution and frame rate mode and a second resolution and frame rate mode. The system also includes switching, in response to the trigger, the video data stream between the first resolution and frame rate mode and the second resolution and frame rate mode, wherein a total horizontal pixel width of each frame of the video data stream in the first resolution and frame rate mode and of each frame of the video data stream in the second resolution and frame rate mode are the same, wherein a pixel clock rate of the video data stream in the first resolution and frame rate mode and the video data stream in the second resolution and frame rate mode are the same.

In some respects, the disclosure is directed to methods and systems for processing signals. A device can include a first circuit configured to process video information for a resolution or scaling operation and provide first data, a second circuit configured to process the video information for the resolution or scaling operation and provide second data, and a third circuit configured to receive the first data and the second data and provide third data according to the resolution or scaling operation, the first circuit comprising a first machine learning engine.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output video conditioned on an input. In one aspect, a method comprises receiving the input; initializing a current intermediate representation; generating an output video by updating the current intermediate representation at each of a plurality of iterations, wherein the updating comprises, at each iteration: processing an intermediate input for the iteration comprising the current intermediate representation using a diffusion model that is configured to process the intermediate input to generate a noise output; and updating the current intermediate representation using the noise output for the iteration.

The invention provides a low earth orbit satellite network video code rate determination method and device and electronic equipment. The method comprises the following steps: acquiring link state information of a low earth orbit satellite network link; predicting whether a link reconstruction event occurs at the next moment based on the link state information; and under the condition of predicting that a link reconstruction event occurs in the low earth orbit satellite network link at the next moment, dividing a time domain into independent control intervals, and independently determining the video block code rate at the next moment based on the network state of the independent control interval in each independent control interval. According to the method, the satellite network reconstruction event is predicted, and the video code rate is independently determined in the interval mode in the reconstruction event period, so that the video live broadcast experience quality in the low-orbit satellite network environment is improved.

Disclosed herein is zero-latency switching between two resolution and frame rate modes. The system includes receiving a trigger to switch a video data stream of frames between a first resolution and frame rate mode and a second resolution and frame rate mode. The system also includes switching, in response to the trigger, the video data stream between the first resolution and frame rate mode and the second resolution and frame rate mode, wherein a total horizontal pixel width of each frame of the video data stream in the first resolution and frame rate mode and of each frame of the video data stream in the second resolution and frame rate mode are the same, wherein a pixel clock rate of the video data stream in the first resolution and frame rate mode and the video data stream in the second resolution and frame rate mode are the same.

The invention discloses a self-adaptive video transmission control method based on unmanned aerial vehicle bandwidth perception. The method comprises the steps that S1, an unmanned aerial vehicle video system sends a bandwidth perception data frame to a ground receiving end; s2, the ground end returns a bandwidth state data frame, wherein the bandwidth state data frame comprises a received signal strength indication (RSSI) and a frame loss rate (FLR) index; s3, the unmanned aerial vehicle video system analyzes the bandwidth state data frame and evaluates the channel quality grade; s4, the unmanned aerial vehicle video system calculates a buffer proportion factor of the annular buffer area; s5, the unmanned aerial vehicle video system calls a pre-constructed adaptive transmission control model, transmission parameters are updated according to the channel quality grade and the buffer proportion factor, and the transmission parameters comprise transmission video quality and coding parameters; s6, transmitting video data according to the updated transmission parameters of the unmanned aerial vehicle video system; and S7, the ground end receives the video data and decodes and plays the video data. According to the invention, the problem of poor adaptability in different network environments when the unmanned aerial vehicle sends the video data with the fixed channel parameters is solved, and the video transmission quality is improved.

The invention relates to the technical field of video processing, and discloses a video super-resolution reconstruction method and device and wearable equipment, and the method comprises the steps: obtaining a to-be-reconstructed low-resolution video; reconstructing the to-be-reconstructed low-resolution video through a preset reconstruction model to obtain a target high-resolution video; wherein the preset reconstruction model at least comprises a disparity map generation module, and the disparity map generation module is used for determining a reference window and a candidate window of the to-be-reconstructed low-resolution video, performing depth information extraction based on the reference window and the candidate window to generate a disparity map, and reconstructing the to-be-reconstructed low-resolution video according to the disparity map. Compared with the prior art that the depth information is not considered, the method can extract the depth information for reconstruction, thereby improving the reconstruction effect.

Examples disclosed herein describe aspect ratio conversion techniques for automated image generation. An image generation request comprising a prompt is received from a user device. A processor-implemented automated image generator may generate a first image based on the prompt. The first image has a first aspect ratio. According to some examples, a region of interest is determined in the first image, based on a prompt alignment indicator for the region of interest. The first image is then processed to obtain a second image. The processing includes an automatic cropping operation directed at the region of interest. The second image has a second aspect ratio that is different from the first aspect ratio. The second image is caused to be presented on the user device.

A method for reducing artifacts in streaming video implemented by a computing device involves determining whether a video quality assessment score for a current segment of a channel of a video stream with a first resolution and a first bit rate meets a quality threshold, replacing the current segment with a replacement segment with a lower resolution than the first resolution, in response to the current segment failing to meet the quality threshold, and publishing the replacement segment at the first bit rate as part of the video stream.

The invention provides a method and a device for outputting single fixed resolution by a VGA (Video Graphics Array) interface of a domestic platform, and belongs to the technical field of circuits. The method comprises the following steps: storing EDID information corresponding to a preset single fixed resolution in an independent EEPROM (Electrically Erasable Programmable Read-Only Memory); the EDID information in the EEPROM is read through an IIC channel of a VGA interface of the processor; configuring a graphics card register according to the EDID information, and outputting a single fixed-resolution VGA video signal corresponding to the EDID information; the display receives and displays the VGA video signal, and only displays the single fixed resolution in a system graphical interface or a terminal command tool. According to the invention, the use requirement of VGA output single fixed resolution is met, and the use safety and reliability are improved.

Systems and techniques are generally described for selecting a machine learning model for compression artifact removal and resolution upscaling of video streaming data. In various examples, a system or method receives a stream of video data, determines a category of the stream of video data based at least partially upon a compression level of the stream of video data, selects weights for a machine learning model based upon the category, and executes the machine learning model with the selected weights to remove compression artifacts in the stream of video data and upscale a resolution of the stream of video data.

The invention relates to the technical field of video processing, and discloses a video super-resolution reconstruction method and device and wearable equipment, and the method comprises the steps: obtaining a to-be-reconstructed low-resolution video; reconstructing the to-be-reconstructed low-resolution video through a preset reconstruction model to obtain a target high-resolution video; wherein the preset reconstruction model at least comprises a channel attention mechanism module provided with a gating mechanism, the gating mechanism comprises target feature weights corresponding to the feature information, the target feature weights are determined through adaptive training, and the channel attention mechanism module is used for performing feature extraction on the low-resolution video to be reconstructed to obtain the feature information; and reconstructing the to-be-reconstructed low-resolution video according to the corresponding target feature weight based on each piece of feature information to obtain a target high-resolution video. When the method is used, reconstruction can be carried out through a gating mechanism according to the target feature weights corresponding to the feature information, so that interference can be reduced, and the reconstruction effect is improved.

The invention relates to electronic communication and connection of a camera to a device. The present disclosure generally relates to managing real-time communication sessions and connecting cameras to devices.

The invention relates to a non-standard JPEG (Joint Photographic Experts Group) coding processing method for dynamic code rate control. The method comprises the following steps: presetting a multi-frame joint image processing scene, obtaining an original reference image, and carrying out combined processing of boundary expansion and random bias addition to obtain a preprocessed reference image; dividing macro blocks for the preprocessed reference image, and distributing an independent coding parameter configuration space after verification and compliance; frequency domain conversion is executed according to a division result, an initial quantization parameter is calculated through an index model, and a dynamic quantization table is dynamically adjusted; executing non-standard entropy coding to obtain an indexed macro block coding code stream; combining the indexed code stream and a macro block division result to construct an index table containing a macro block serial number, an initial address and a code stream length; analyzing the code stream to obtain quantized data, and performing inverse quantization by using a dynamic quantization table to obtain spatial domain data; enabling the format of the reconstructed image to be consistent with that of the preprocessed reference image through reverse preprocessing, and performing real-time processing on the linkage input image to obtain a reconstructed reference image; and non-standard JPEG coding processing of dynamic code rate control is realized.

The invention relates to the technical field of video processing, and discloses a video super-resolution reconstruction method and device and wearable equipment, and the method comprises the steps: obtaining a to-be-reconstructed low-resolution video; reconstructing the to-be-reconstructed low-resolution video through a preset reconstruction model to obtain a target high-resolution video; wherein the preset reconstruction model at least comprises a dense module and a non-local attention module, the dense module is used for performing feature extraction on the to-be-reconstructed low-resolution video and reconstructing the to-be-reconstructed low-resolution video according to the first extraction result to obtain an initial high-resolution video, and the non-local attention module is used for performing non-local attention on the initial high-resolution video; and the non-local attention module is used for determining the relevance of the initial high-resolution video by adopting a self-attention mechanism, and adjusting the initial high-resolution video based on the relevance to obtain a target high-resolution video. According to the method and the device, the relevance of different positions can be considered in the obtained target high-resolution video, so that the reconstruction effect is improved.

A mechanism for processing video data is disclosed. The mechanism includes determining a horizontal scaling ratio of a neural-network post-filter (NNPF) and a vertical scaling ratio of the NNPF are indicated in a bitstream when a NNPF process employs spatial resolution upsampling. A conversion is performed between a visual media data and a bitstream based on the horizontal scaling ratio and the vertical scaling ratio.

A video encoding / decoding method, a bitstream transmission method, and a computer-readable recording medium for storing a bitstream are provided. The video decoding method according to this disclosure is a video decoding method performed by a video decoding device, and includes the steps of: obtaining size information from an NNPFC (neural-network post-filter characteristics) SEI (supplemental enhancement information) message; and determining the size of an output picture based on the size information, wherein the size information includes information for the numerator of the ratio between the size of the output picture and the size of the input picture and information for the denominator of the ratio.

In some respects, the disclosure is directed to methods and systems for processing signals. A device (200) can include a first circuit configured to process video information for a resolution or scaling operation and provide first data, a second circuit configured to process the video information for the resolution or scaling operation and provide second data, and a third circuit configured to receive the first data and the second data and provide third data according to the resolution or scaling operation. the first circuit comprising a first machine learning engine (402).

Described herein are systems and methods of converting media dimensions. A device may identify a set of frames from a video in a first orientation as belonging to a scene. The device may receive a selected coordinate on a frame of the set of frames for the scene. The device may identify a first region within the frame including a first feature corresponding to the selected coordinate and a second region within the frame including a second feature. The device may generate a first score for the first feature and a second score for the second feature. The first score may be greater than the second score based on the first feature corresponding to the selected coordinate. The device may crop the frame to include the first region and the second region within a predetermined display area comprising a subset of regions of the frame in a second orientation.

The embodiment of the invention discloses a video monitoring method and device, electronic equipment and a storage medium. The method comprises the following steps: receiving a monitoring demand instruction sent by a user terminal in real time; screening at least one key video frame matched with the target attention dimension from a real-time video stream acquired by a camera; inputting the monitoring demand instruction and the at least one key video frame into a pre-trained analysis large model, extracting feature information of the target object under the target attention dimension through the analysis large model, and generating a structured description text containing the feature information; the structured description text and a thumbnail of the at least one key video frame are packaged into a monitoring result package, the monitoring result package is output to a terminal corresponding to the user, and the thumbnail is an image obtained after resolution compression processing is conducted on the key video frame. According to the scheme, the demand pertinence, the result structuring degree and the data security of video monitoring can be improved.

Video conversion technology, in which a first stream of video content is accessed and multiple, different layers are extracted from the first stream of the video content. Each of the multiple, different layers are separately processed to convert the multiple, different layers into modified layers that each have a higher resolution. The modified layers are reassembled into a second stream of the video content that has a higher resolution than the first stream of the video content.

A method causes a display device to simultaneously display (1) a video scene including a plurality of items depicted in the video scene; (2) a first tag in a first position in the video scene; and (3) a second tag in a second position, distinct from the first position, in the video scene. The first tag is associated with one of the items in the video scene. The second tag is associated with one of the items in the video scene. The second tag appears distinct and separated away from its associated item in the video scene. The second tag includes text information describing its associated item in the video scene.

A video data processing method includes receiving compressed video data that has first resolution, obtaining first texture data having the first resolution based on one or more first video frames in the compressed video data, generating second texture data having second resolution higher than the first resolution based on the first texture data, and generating one or more second video frames having the second resolution through a rendering operation and based on the second texture data.

The present disclosure provides methods, apparatuses, and systems for processing content for multiple displays. The present implementation is more particularly directed to outputting video content from a mobile computing device to a plurality of displays coupled to a docking station. In some aspects, a multi-screen controller for a mobile computing device may receive pixel data associated with a plurality of displays from one or more image sources, and may aggregate the received pixel data into a plurality of frames associated with the plurality of displays, respectively. The multi-screen controller transcodes each frame of pixel data from a first video coding format associated with one or more image sources to a second video coding format associated with a docking station coupled to the display, and outputting each frame of transcoded pixel data to a docking station for display on a respective one of the displays.

To provide video processing and playback systems and methods.SOLUTION: A video processing method is for processing a circular panoramic recording video including an original field of view region at a first resolution and a further peripheral region outside the original field of view region at a second resolution lower than the first resolution, and includes a step of performing spatial upscaling of the further peripheral region to a resolution higher than the second resolution.SELECTED DRAWING: Figure 15

The invention discloses a spare image generation method, a coding method, a coding device and equipment, and belongs to the technical field of image processing, the spare image generation method of the embodiment of the invention comprises the following steps: decoding reference image information and gain image information respectively to obtain a first reference image and a first gain image; and executing a first operation based on the first reference map and the first gain map, and generating a first standby map based on the first operation.

In some respects, the disclosure is directed to methods and systems for processing signals. A device can include a first circuit configured to process video information for a resolution or scaling operation and provide first data, a second circuit configured to process the video information for the resolution or scaling operation and provide second data, and a third circuit configured to receive the first data and the second data and provide third data according to the resolution or scaling operation, the first circuit comprising a first machine learning engine.

A computing system (100) is provided, including a camera (30) configured to capture a series of images in a video stream, processing circuitry (12), and an image processing pipeline (22) including a preprocessing module (24) and an encoder (120), in which the preprocessing module (24) is configured to receive the video stream from the camera (30) at a camera-native video data rate parameter. The processing circuitry (12) is configured to communicate with a server (16) to establish a joint video communication session with remote client devices (18) and receive a requested video data rate parameter (20) from the server (16) for the video stream captured by the camera (30). The processing circuitry (12) is further configured to send a command to the preprocessing module (24) to adjust the camera-native video data rate parameter of the video stream to the requested video data rate parameter (20) and preprocess the video stream at the requested video data rate parameter (20) and pass the preprocessed video stream to the encoder (120).

A mechanism for processing video data is disclosed. The mechanism includes determining to pass parameters to a neural-network post-filter (NNPF) when the NNPF is activated. A conversion is performed between a visual media data and a bitstream based on the parameters. The parameters may be referred to as activation parameters when the parameters are passed to the NNPF upon activation.