Video decoding method, system and medium
A video decoding and decoding technology, applied in the field of systems and media, and video decoding methods, can solve problems such as large amount of calculation
Pending Publication Date: 2021-08-24
ALIBABA SINGAPORE HLDG PTE LTD
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, even for compressed video, processing it through machine learning techniques can be computationally intensive
Current technology applications often result in large volumes of video data being captured, much of which may not be relevant to computer vision and machine vision computing
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The systems and methods discussed herein are aimed at enabling video decoders that output reduced image data, and more specifically, enabling selective frame output and downsampling by video decoders, and output of motion prediction information by video decoders.
[0046] According to an exemplary embodiment of the present disclosure, a learning model may be a defined computing algorithm executable by one or more processors of a computing system to perform a learning task including processing inputs with various parameters and outputting results. For example, the learning model may be a hierarchical model such as a deep neural network, which may have a fully connected structure, may have a feed-forward structure such as a convolutional neural network (CNN), may have a reverse Propagation structures, or other architectures that can have computations tailored to specific learning tasks. Learning tasks may include, for example, classification, clustering, matching, regress...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a video decoding method and system, and a medium. A video decoder obtains encoded frames of captured video from a bitstream, but outputs only a subset of the frames from the bitstream as a downsampled frame based on several image data reduction parameters, as opposed to conventional decoder behavior. Further, the video decoder bypasses the decoding path by outputting the motion prediction information encoded in the video bitstream in place of (or in addition to) the reconstructed frame. Reduced output image data may mitigate or eliminate excess computational workloads at a video decoder running on a computing system implementing a learning model for computer vision or machine vision applications, as properties of the computational workloads do not contribute to the computation of learning tasks. Thus, the computational efficiency of a computing system configured for computer vision or machine vision applications may be improved.
Description
technical field [0001] The present disclosure relates to the fields of computer vision and machine vision, and in particular to a video decoding method, system and medium. Background technique [0002] Computer vision and machine vision technologies, in fields as diverse as image and object recognition for autonomous vehicles, medical imaging, facial recognition, content-based image search, etc., rely on the capture of video data to observe over time objects and scenes. However, feeds of raw images captured by video capture devices such as cameras and sensors contain many frames of dense image data. [0003] Traditionally, image data is captured not in raw form, but as a sequence of frames encoded by video compression algorithms such as H.264 / AVC (Advanced Video Coding) standards, H.265 / HEVC (High Efficiency Video Coding) standards, etc. Composed in compressed form, to be stored or transmitted frame by frame. Raw image data is encoded to produce a bitstream in which uncom...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04N19/114H04N19/132H04N19/186H04N19/44
CPCH04N19/114H04N19/132H04N19/186H04N19/44
Inventor 秦明海王佳陈平李思成方元炜陈彦光顾震宇谢文张洁靖王文特张经纬
Owner ALIBABA SINGAPORE HLDG PTE LTD