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

Full-reference video quality assessment method based on motion trajectory

A motion trajectory and video quality technology, applied in TV, selective content distribution, electrical components, etc., can solve the problems of not considering the characteristics of human motion perception, poor stability, etc., to reduce computational complexity and memory consumption Effect

Active Publication Date: 2019-12-10
XIDIAN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because these methods do not take into account the characteristics of human motion perception, the quality evaluation results are difficult to be consistent with human subjective perception results, and the evaluation stability is poor.

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
  • Full-reference video quality assessment method based on motion trajectory
  • Full-reference video quality assessment method based on motion trajectory
  • Full-reference video quality assessment method based on motion trajectory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0038] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0039] Step 1, will refer to the video V r Draw V with the test video d Divide into sequence fragments according to the same length.

[0040]Test video V d and reference video V r Usually there are 150 to 600 frames. In this example, according to the length of L=18 frames, the test video and the reference video are divided into n sequence segments: V d ={V 1 d ,...,V i d ,...V n d}, Among them, V i d Denotes the i-th test sequence segment, V i r Indicates the i-th reference sequence segment, i=1, 2, . . . , n, n≥2 and n is an integer.

[0041] Step 2, calculate the i-th test sequence segment V i d The static quality estimate Qs of i .

[0042] The static information is presented in the form of an image of each frame, and its static qua...

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 full-reference video quality evaluation method based on a movement locus and mainly solves the problems that existing technological evaluation has low accuracy and high calculation complexity. The full-reference video quality evaluation method is characterized by comprising the steps: dividing a test video and a reference video into equal-length sequence fragments; calculating out the static quality of the test sequence fragment; point sampling a first frame of the test sequence fragment; respectively calculating out luminous fluxes of the test sequence fragment and the reference sequence fragment; calculating out the movement locus of a sampling point in the reference sequence fragment and removing the invalid locus in the movement locus; respectively extractingthe luminous flux characteristics along the movement locus of the test sequence fragment and the reference sequence fragment and calculating out the characteristic difference between the test sequencefragment and the reference sequence; calculating out the dynamic quality of the test sequence fragment; calculating out the test video quality according to the static quality and the dynamic qualityof the sequence fragments. The full-reference video quality evaluation method disclosed by the invention can improve quality evaluation accuracy, simultaneously reduces calculation complexity and canbe applied to quality detection evaluation in video compression, transmission and treatment.

Description

technical field [0001] The invention belongs to the technical field of image and video processing, in particular to a full-reference video quality evaluation method, which can be used for quality detection and evaluation in video compression, transmission and processing. [0002] technical background [0003] With the development of handheld smart devices and the advancement of network communication technology, WeChat video, mobile phone camera, webcast, etc. have been integrated into people's daily life. Due to the limitations of network bandwidth and storage device capacity, video usually needs to be compressed and encoded before transmission and processing. On the one hand, due to the influence of hardware equipment, the video will inevitably be disturbed by noise during the shooting process, which will affect the quality of the video; on the other hand, some original information will be lost when the video is compressed; at the same time, during video transmission When a...

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): H04N21/234H04N21/44H04N17/00
CPCH04N17/00H04N21/23418H04N21/44008
Inventor 吴金建刘永旭谢雪梅石光明
Owner XIDIAN UNIV