No-reference video quality evaluation method and device

A video quality and video technology, applied in the video field, can solve the problems of less application, large calculation time, complex algorithm modeling, etc., and achieve the effect of small calculation amount and high engineering application value.

Inactive Publication Date: 2014-01-22
ALIBABA (CHINA) CO LTD
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this type of algorithm is complex in modeling, time-consuming in operation, and difficult to inte...

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
  • No-reference video quality evaluation method and device
  • No-reference video quality evaluation method and device
  • No-reference video quality evaluation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] 1280x720 H.264 High Profile compressed "Painted Skin 2" movie original version A and gun version B:

[0099] The main calculation steps are as follows:

[0100] 1. By analyzing the video file, the encoding format of the video is obtained: VCF = H264 High profile, bit rate: VCB = 2000kpbs, resolution: VF = 1280x720;

[0101]2. Perform one-pass transcoding, and the peak signal-to-noise ratio of the video after one-pass transcoding is: OPSNR = 45db;

[0102] 3 Carry out the detection of video blur and block effect, and the blur degree BV of the original version A is 0.377099; the block effect DV is 0.251446; the blur degree BV of the gun version B is 0.0771028;

[0103] 4 According to the code rate conversion relationship in Table 1, obtain the code rate loss rate loss_factor = 1 corresponding to the video coding format H264;

[0104] 5 Calculate the bit rate video dynamic weighting factor VMF:

[0105] 5.1 Set the peak signal-to-noise ratio BPSNR value of the reference...

Embodiment 2

[0126] 4M bit rate video A compressed by 720x576 MPEG2 Main Profile, and 2M bit rate video B compressed by 720x576 H.264 Main Profile:

[0127] The main calculation steps are as follows:

[0128] 1 By analyzing the video file, we get:

[0129] Video A: encoding format VCF = Mpeg2 Main profile, bit rate VCB = 4000kpbs, resolution VF = 720x576;

[0130] Video B: encoding format VCF = H264 Main profile, bit rate VCB = 2000kpbs, resolution VF = 1920x1080;

[0131] 2 Perform one-pass transcoding to obtain the peak signal-to-noise ratio of the video after one-pass transcoding:

[0132] Video A: OPSNR = 41db

[0133] Video B: OPSNR = 37.55db

[0134] 3 Carry out the detection of video blur and block effect, and the detection results show that the blur BV of the original version A is 0.467216; the block effect DV is 0.293094, and the blur BV of the gun version B is 0.603774;

[0135] 4 According to the bit rate conversion relationship in Table 1, obtain the bit rate loss rate los...

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 no-reference video quality evaluation method and device. The method comprises the steps as follows: analyzing and acquiring an encoding format, an encoding rate and a resolution ratio of a video; acquiring video source data; acquiring OPSNR (optical signal noise ratio) after encoding is finished; searching a loss rate list of code rates of the encoding format according to the acquired video encoding format so as to obtain a corresponding code-rate loss rate; computing a dynamic video weighting factor; performing code rate conversion to obtain a dynamic weighting code rate; substituting a converted code rate and the video resolution ratio into a video quality evaluation score list to obtain a dynamic video benchmark score through searching; acquiring a fuzzy coefficient by means of the video source data, and acquiring a video ambiguity benchmark score; and acquiring a final score through weighting addition of the dynamic video benchmark score and the video ambiguity benchmark score. The quality evaluation device can be simply and conveniently accessed to a universal video encoding and decoding structure system, the computation amount is small, and original video information is not required to be used as reference, so that a higher engineering application value is achieved.

Description

technical field [0001] The present invention relates to the field of video technology, in particular, to a method and device for evaluating video quality without reference. Background technique [0002] With the rapid development of digital image compression coding technology, image compression can be regarded as a compromise between bit rate, image quality, visual perception distortion and algorithm complexity. The design of image compression algorithm mainly depends on the above three factors . And image quality visual perception distortion has always been a weak link in the research work. At the same time, in the process of image acquisition, compression, processing, transmission and reproduction, data distribution in the process of storage and communication of digital video or image data is prone to various distortions. For example, lossy video compression techniques may reduce their quality during the quantization process. Therefore, it is very necessary to be able t...

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
IPC IPC(8): H04N19/154H04N17/00H04N19/53
Inventor 泉源焦华龙高飞汤宁姚健潘柏宇卢述奇
Owner ALIBABA (CHINA) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products