12 results about "Variable frame rate" patented technology

Methods and systems for frame rate scalability are described. Support is provided for input and output video sequences with variable frame rate and variable shutter angle across scenes, or for input video sequences with fixed input frame rate and input shutter angle, but allowing a decoder to generate a video output at a different output frame rate and shutter angle than the corresponding input values. Techniques allowing a decoder to decode more computationally-efficiently a specific backward compatible target frame rate and shutter angle among those allowed are also presented.

A variable frame rate video generation method based on optical flow estimation, which introduces optical flow supervision information into an OpFode-Net model, the OpFode-Net model comprising an encoder-decoder structure; the encoder uses an ODE-ConvGRU to embed input video sequence X T into a hidden state h T ; wherein the ODE-ConvGRU uses a ConvGRU as a node of a neural ODE and embeds it into the neural ODE to realize dynamic modeling of the video sequence; the decoder starts from h T , and uses an ODE solver to generate a new video frame at any time step S, which can realize more accurate prediction results and achieve optimal performance in video interpolation and video prediction tasks.

A neural TTS system is trained to generate key acoustic frames at variable rates while omitting other frames. The frame skipping depends on the acoustic features to be generated for the input text. The TTS system can interpolate frames between the key frames at a target rate for a vocoder to synthesis audio samples.

The present application provides a variable frame rate human motion analysis processing method, device and equipment, the method comprises: acquiring a preset frame rate motion video file; each video frame image in the motion video file is recognized to obtain a three-dimensional motion data model set based on time domain; the motion video file is divided according to preset frame rate distribution rule, to determine the target frame rate corresponding to the motion video file in different time periods; the frame rate of the motion video file in different time periods is converted into the corresponding target frame rate, to determine the frame rate set of the motion video file; the three-dimensional motion data model set and the frame rate set are encapsulated to obtain an encapsulation file, so that the user can analyze the motion data through the encapsulation file, the present application adopts a variable frame rate processing mode, dynamically analyzes and processes according to the actual motion type, and ensures the accuracy of model data and the timeliness of processing as far as possible.

Methods and systems for frame rate scalability are described. Support is provided for input and output video sequences with variable frame rate and variable shutter angle across scenes, or for input video sequences with fixed input frame rate and input shutter angle, but allowing a decoder to generate a video output at a different output frame rate and shutter angle than the corresponding input values. Techniques allowing a decoder to decode more computationally-efficiently a specific backward compatible target frame rate and shutter angle among those allowed are also presented.

A neural TTS system is trained to generate key acoustic frames at variable rates while omitting other frames. The frame skipping depends on the acoustic features to be generated for the input text. The TTS system can interpolate frames between the key frames at a target rate for a vocoder to synthesis audio samples.

The application discloses an avian influenza host bird behavior prediction method based on deep reinforcement learning, comprising the following steps: S1, deploying multi-angle and variable frame rate cameras in the target habitat to collect multi-source video data; S2, performing frame insertion, illumination normalization and background denoising processing on the video data; S3, inputting the pretreated data into an improved YOLOv5 model to obtain target detection results; S4, constructing a dynamic graph neural network based on bird nodes and space-time edges to output a flocking tendency vector; S5, inputting the flight trajectory into a low-level Actor-Critic policy network to generate a local short-term behavior decision; S6, combining the flocking tendency vector and historical error feedback to generate a global multi-step behavior prediction sequence; and S7, comparing the prediction results with actual observation data and triggering online fine-tuning according to the deviation. The application can realize non-invasive and high-precision bird behavior prediction and is suitable for avian influenza monitoring and early warning scenes.

The present application provides an application loading method and an electronic device. The application loading method comprises: detecting that a target application enters a loading phase; in response to the target application entering the loading phase, loading the target application at a variable frame rate, wherein the frame rate of each frame in the loading phase is determined on the basis of an operating duration of each frame, and at least one frame in the loading phase has a frame rate higher than a preset frame rate; and if a loading page of the target application is a blank screen, acquiring a first loading page and displaying the first loading page in the loading phase. The method of the present application can increase the application loading speed. When the loading page is the blank screen, an electronic device displays the first loading page to prevent a user from viewing the blank screen in the loading phase, thereby improving the entertainment experience of the user.

Methods and systems for frame rate scalability are described. Support is provided for input and output video sequences with variable frame rate and variable shutter angle across scenes, or for input video sequences with fixed input frame rate and input shutter angle, but allowing a decoder to generate a video output at a different output frame rate and shutter angle than the corresponding input values. Techniques allowing a decoder to decode more computationally-efficiently a specific backward compatible target frame rate and shutter angle among those allowed are also presented.

Video visualization systems with customizable image sensor frame rates to output multiple imaging modalities. A system includes an image sensor and an emitter. The system includes a controller that synchronizes operations of the emitter and the image sensor to output a video stream comprising data from one or more of a plurality of possible imaging modalities including color video imaging data, fluorescence video imaging data, and multispectral video imaging data. The controller selects a frame rate for the image sensor to output a video stream comprising two or more requested imaging modalities requested by a user, and further based on a minimum required frame rate for each of the two or more requested imaging modalities.

The invention relates to a signal processing device and a vehicle display device having the same. A signal processing apparatus according to an embodiment of the present invention comprises: at least one neural processor; the central processing unit runs a virtual machine monitoring program; the central processing unit runs a plurality of virtual machines on the virtual machine monitoring program; a first virtual machine of the plurality of virtual machines is controlled to operate the neural processor at a variable frame rate or output result data based on sensor data from a sensor device in the vehicle. As a result, the neural processor can operate efficiently.

A method for reading and writing frame images having variable frame rates and a system therefor are provided. The system provides a video processing system that includes a write end and a read end for accessing a single buffer block. In the method performed in the video processing system, when the read end starts to read an image frame, the read end is controlled to not read data from the buffer block until the data written by the write end to the buffer block reaches a progress threshold; and when it is determined that a portion of the data in the buffer block not yet read by the read end will be overwritten by the data written by the write end, the writing process is terminated until the read end finishes reading the data in the portion in the buffer block.