A Visual Sensitivity Aware ABR Algorithm for DASH via Deep Reinforcement Learning

doi:10.1145/3591108

2023-11-10

PRE

DOI：10.1145/3591108

原文求助

摘要

En 中文

In order to cope with the fluctuation of network bandwidth and provide smooth video services, adaptive video streaming technology is proposed. In particular, the adaptive bitrate (ABR) algorithm is widely used in dynamic adaptive streaming over HTTP (DASH) to improve quality of experience (QoE). However, existing ABR algorithms still ignore the inherent visual sensitivity of human visual system (HVS). As the final receiver of video, HVS has different sensitivity to the quality distortion of different video content, and video content with high visual sensitivity needs to allocate more bitrate resources. Therefore, existing ABR algorithms still have limitations in reasonably allocating bitrate and maximizing QoE. To solve this problem, this paper designs an adaptive bitrate strategy from the perspective of user vision, studies the modeling of visual sensitivity, and proposes a visual sensitivity aware ABR algorithm. We extract a set of content features and attribute features from the video, and consider the simulation of HVS to establish a total masking effect model that reflects the visual sensitivity more accurately. Further, the network status, buffer occupancy, and visual sensitivity are comprehensively considered under a deep reinforcement learning framework to select the appropriate bitrate for maximizing QoE. We implement the proposed algorithm over a realistic trace-driven evaluation and compare its performance with several latest algorithms. Experimental results show that our algorithm can align ABR strategy with visual sensitivity to achieve better QoE in high visual sensitivity content, and improves the average perceptual video quality and overall user QoE by 18.3% and 22.8%, respectively. Additionally, we prove the feasibility of our algorithm through subjective evaluation in the real environment.

Keyword:

ABR

DASH

QoE

visual sensitivity

deep reinforcement learning