VATP360: Viewport Adaptive 360-Degree Video Streaming based on Tile Priority

TL;DR

This paper introduces VATP360, a viewport adaptive streaming method for 360-degree videos that predicts user viewports using object trajectories and allocates bitrates via reinforcement learning, improving streaming efficiency.

Contribution

The paper presents a novel viewport prediction and tile prioritization framework that enhances 360-degree video streaming by balancing performance and computational overhead.

Findings

Accurate viewport prediction using object motion trajectories.

Effective tile priority classification reduces computational complexity.

Reinforcement learning-based bitrate allocation improves streaming quality.

Abstract

360-degree video becomes increasingly popular among users. In the current network bandwidth, serving high resolution 360 degree video to users is quite difficult. Most of the work has been devoted to the prediction of user viewports or tile-based adaptive algorithms. However, it is difficult to predict user viewports more accurately using only information such as user's historical viewports or video saliency maps. In this paper, we propose a viewport adaptive 360-degree video streaming method based on tile priority (VATP360), which tries to balance between the performance and the overhead. The proposed VATP360 consists of three main modules: viewport prediction, tile priority classification and bitrate allocation. In the viewport prediction module, object motion trajectory and predicted user's region-of-interest (ROI) are used to achieve accurate prediction of the user's future viewport. Then, the predicted viewport, along with the object motion trajectory, are fed into the proposed tile priority classification algorithm to assign different priorities to tiles, which would reduce the computational complexity of the bitrate allocation module. Finally in the bitrate allocation stage, we adaptively assign bitrates to tiles of different priority by reinforcement learning. Experimental results on publicly available datasets have demonstrated the effectiveness of the proposed method.