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

A Video Quality Evaluation Algorithm Based on 3D Gradient Similarity

A technology of video quality and similarity, applied in TV, electrical components, image communication, etc., to achieve real-time quality evaluation, low computational complexity, and good video evaluation performance

Inactive Publication Date: 2017-09-15
TIANJIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Generally speaking, although some achievements have been made in video quality evaluation, there are still many technical problems and further development and improvement are needed.

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 Video Quality Evaluation Algorithm Based on 3D Gradient Similarity
  • A Video Quality Evaluation Algorithm Based on 3D Gradient Similarity
  • A Video Quality Evaluation Algorithm Based on 3D Gradient Similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solution of the present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0031] Compared with static images, video sequences have some complex temporal changes, so the video quality evaluation algorithm based on three-dimensional gradient similarity (Three-Dimensional Gradient Similarity, 3DSIM) of the present invention introduces temporal gradients into the FSIM image evaluation algorithm. Operators are used to calculate the temporal gradient similarity, and a video quality evaluation model based on three-dimensional gradient similarity is proposed, and the final 3DSIM value is used as the video quality score.

[0032] The three-dimensional gradient operator that the present invention intends to adopt is as figure 2 shown. Among them, the current frame f t The gradient operator of (x) is g t ; Adjacent to the previous two frames f t-2 (x), f t-1 The gradient operators of (x...

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 video quality evaluation algorithm based on three-dimensional gradient similarity, which respectively calculates the three-dimensional gradient similarity matrix, phase consistency similarity matrix and gradient similarity matrix of the corresponding frames of the original video and the distorted video, and calculates the three-dimensional gradient Similarity 3DSIM is used as the evaluation of video quality to complete the quality evaluation of distorted video. Compared with the prior art, the present invention improves the consistency between the objective quality evaluation of video and the subjective quality evaluation of human eyes. The algorithm is not limited to the video quality evaluation of specific scenes, and has better performance on video sequences with different distortion types. The performance of video evaluation; in addition, the algorithm has low computational complexity and can realize real-time quality evaluation.

Description

technical field [0001] The invention relates to the field of video quality evaluation, in particular to a video quality evaluation algorithm based on three-dimensional gradient similarity. Background technique [0002] Video quality evaluation plays an extremely important role in optimizing video acquisition, compression, transmission and storage. Video quality evaluation is mainly divided into objective quality evaluation and subjective quality evaluation. The former evaluates the video quality through quantitative indicators given by the algorithm; the latter measures the video quality based on the subjective feelings of the observer. Because subjective quality evaluation is time-consuming and laborious, objective quality evaluation algorithms are usually used to evaluate video quality in practical applications, and the consistency between the evaluation results and subjective quality evaluation results is used as a performance index to measure the objective evaluation al...

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): H04N17/00
Inventor 张淑芳韩泽欣王馥瑶张聪
Owner TIANJIN UNIV