Abstract

In the present study the video content and quality monitoring issue is studied. For this purpose, the contents and qualities of two video streams must be compared with each other. It is clear that achieving to a monitoring system will be possible by utilizing multimodal information from the video streams. Therefore, simultaneous evaluation of the image and audio signals is vital. This comparative study for image signal is based on the extraction of useful features such as texture using Gabor filter. In order to create differences between two video streams in terms of content, some frames are added to or eliminated from the original video. Moreover, distortions such as blurring, packet loss and adding three types of noises are done as attacks to the original videos in order to make difference in terms of quality. Three types of additive noises such as Gaussian, Poisson and Speckel are used to produce noisy images for the purpose of comparing with the original ones. The audio signals of the two compared video streams are evaluated using PESQ similarity measurement. Finally, these parameters are characterized on the basis of some statistical standard image quality matrices like SNR, Correlation coefficient and SSIM. The results illustrate that the proposed method is effective and highly reliable against various kinds of noises.

Keywords:

Gabor filter, PESQ, SSIM, texture extraction, video monitoring,

References

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.