Network state Estimation using Raw Video Analysis: vQoS-GAN based non-intrusive Deep Learning Approach

TL;DR

This paper introduces vQoS-GAN, a semi-supervised deep learning model that estimates network degradation parameters from degraded videos and reconstructs the original video to improve streaming quality.

Contribution

The paper presents a novel semi-supervised GAN model for non-intrusive network state estimation directly from video data, with high accuracy and reconstruction capabilities.

Findings

Achieved over 95% training accuracy in estimating network parameters.

Successfully reconstructed degraded videos to original quality.

Demonstrated effectiveness in real-time video streaming scenarios.

Abstract

Content based providers transmits real time complex signal such as video data from one region to another. During this transmission process, the signals usually end up distorted or degraded where the actual information present in the video is lost. This normally happens in the streaming video services applications. Hence there is a need to know the level of degradation that happened in the receiver side. This video degradation can be estimated by network state parameters like data rate and packet loss values. Our proposed solution vQoS GAN (video Quality of Service Generative Adversarial Network) can estimate the network state parameters from the degraded received video data using a deep learning approach of semi supervised generative adversarial network algorithm. A robust and unique design of deep learning network model has been trained with the video data along with data rate and packet loss class labels and achieves over 95 percent of training accuracy. The proposed semi supervised generative adversarial network can additionally reconstruct the degraded video data to its original form for a better end user experience.