Unlock instant, AI-driven research and patent intelligence for your innovation.

A Content-Based Bitstream Layer Video Quality Evaluation Model

A video quality and bitstream layer technology, applied in the multimedia field, can solve the problems of a large amount of video data, the database cannot be reached, and the deep learning has no video quality evaluation direction to gain more recognition and achievements.

Active Publication Date: 2021-11-26
BEIJING UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deep learning requires a large amount of video data, and commonly used databases cannot reach this order of magnitude
In addition, there is still no complete scientific theory to support the feasibility of deep learning, so deep learning has not gained more recognition and achievements in the direction of video quality evaluation

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Content-Based Bitstream Layer Video Quality Evaluation Model
  • A Content-Based Bitstream Layer Video Quality Evaluation Model
  • A Content-Based Bitstream Layer Video Quality Evaluation Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0061] Embodiment 1 studies the relationship between subjective perceptual quality and the quantization parameter QP; Embodiment 2 uses the proportion of small-sized prediction blocks SPM_Ratio and the proportion of non-zero DCT coefficients contained in each 4×4 block in an I frame to describe the video The spatial complexity of the sequence; Embodiment 3 uses the motion vector information suffix average length normalization parameter Ave_Mvlen to describe the time complexity of the video sequence; Embodiment 4 is based on the relationship between subjective perception quality and QP, and uses the least squares method to train related parameters , and finally establish the video quality evaluation model formula.

[0062] S1. Perceptual Quality and Quantization Parameters

[0063] Since H.264 is a block-based DCT compression method, block distortion is the most important coding distortion, so quantization is closely related to coding distortion and perceived quality. There ar...

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

No PUM Login to View More

Abstract

The invention discloses a content-based bit stream layer video quality evaluation model, which belongs to the technical field of multimedia. The compressed domain model can directly extract video parameters from the code stream for real-time non-intrusive quality monitoring. The model is mainly aimed at the H.264 video coding standard and is used for quality evaluation of coding distortion. A fundamental relationship between perceptual quality and the quantization parameter QP is established. Considering the apparent dependence of perceptual quality on video content, video content is defined as a combination of different temporal and spatial complexities. The present invention uses the ratio SPM_Ratio of small-sized prediction blocks and the ratio Ave_Coef of DCT non-zero numbers contained in each 4×4 block in an I frame to describe the spatial complexity of the video at the same time. Use the normalized parameter Ave_Mvlen of the average suffix length of the motion vector information in the code stream to describe the space complexity of the video. All information can be extracted directly from the bitstream without decoding.

Description

technical field [0001] The invention proposes a video quality evaluation model based on a compressed domain, which belongs to the technical field of multimedia. Background technique [0002] In recent years, with the vigorous development of multimedia technology, network video services, videophone, IPTV, etc. have gained obvious popularity in our daily life. However, the quality of these applications often cannot be monitored and guaranteed in real time. Therefore, it is very necessary to establish an objective model for network video quality assessment. [0003] From the perspective of whether original video information is needed, video quality evaluation can be divided into subjective evaluation and objective evaluation. Subjective evaluation requires the subjects to observe a series of tested videos in a specific environment and score according to the pre-specified scoring standards. The main methods are: DSIS (Double Stimulus Impairment Scale) method, DSCQS (Double St...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N19/154H04N17/00
CPCH04N17/004H04N19/154
Inventor 李晨昊张美娜
Owner BEIJING UNIV OF TECH