Human-Perception-Oriented Pseudo Analog Video Transmissions with Deep Learning

TL;DR

This paper introduces ROIC-Cast, a human-perception-oriented pseudo analog video transmission system that enhances region-of-interest quality using deep learning-based saliency detection, efficient compression, and adaptive power allocation, outperforming existing methods.

Contribution

It presents a novel system integrating saliency detection, data compression, and optimal power allocation for perceptually optimized pseudo analog video transmission.

Findings

ROIC-Cast achieves over 4.1dB PSNR gains for ROI.

Significant performance improvement over existing systems.

Effective ROI extraction and adaptive power allocation enhance video quality.

Abstract

Recently, pseudo analog transmission has gained increasing attentions due to its ability to alleviate the cliff effect in video multicast scenarios. The existing pseudo analog systems are sorely optimized under the minimum mean squared error criterion without taking the perceptual video quality into consideration. In this paper, we propose a human-perception-based pseudo analog video transmission system named ROIC-Cast, which aims to intelligently enhance the transmission quality of the region-of-interest (ROI) parts. Firstly, the classic deep learning based saliency detection algorithm is adopted to decompose the continuous video sequences into ROI and non-ROI blocks. Secondly, an effective compression method is used to reduce the data amount of side information generated by the ROI extraction module. Then, the power allocation scheme is formulated as a convex problem, and the optimal transmission power for both ROI and non-ROI blocks is derived in a closed form. Finally, the simulations are conducted to validate the proposed system by comparing with a few of existing systems, e.g., KMV-Cast, SoftCast, and DAC-RAN. The proposed ROIC-Cast can achieve over 4.1dB peak signal- to-noise ratio gains of ROI compared with other systems, given the channel signal-to-noise ratio as -5dB, 0dB, 5dB, and 10dB, respectively. This significant performance improvement is due to the automatic ROI extraction, high-efficiency data compression as well as adaptive power allocation.