inis 22(4): e2

Research Article

An Accurate Viewport Estimation Method for 360 Video Streaming using Deep Learning

Download24 downloads
  • @ARTICLE{10.4108/eetinis.v9i4.2218,
        author={Hung Nguyen and Thu Ngan Dao and Ngoc Son Pham and Tran Long Dang and Trung Dung Nguyen and Thu Huong Truong},
        title={An Accurate Viewport Estimation Method for 360 Video Streaming using Deep Learning},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems},
        volume={9},
        number={4},
        publisher={EAI},
        journal_a={INIS},
        year={2022},
        month={9},
        keywords={},
        doi={10.4108/eetinis.v9i4.2218}
    }
    
  • Hung Nguyen
    Thu Ngan Dao
    Ngoc Son Pham
    Tran Long Dang
    Trung Dung Nguyen
    Thu Huong Truong
    Year: 2022
    An Accurate Viewport Estimation Method for 360 Video Streaming using Deep Learning
    INIS
    EAI
    DOI: 10.4108/eetinis.v9i4.2218
Hung Nguyen1, Thu Ngan Dao1, Ngoc Son Pham2, Tran Long Dang3, Trung Dung Nguyen2, Thu Huong Truong2,*
  • 1: East Asia University of Technology, Vietnam
  • 2: Hanoi University of Science and Technology
  • 3: University of Greenwich
*Contact email: huong.truongthu@hust.edu.vn

Abstract

Nowadays, Virtual Reality is becoming more and more popular, and 360 video is a very important part of the system. 360 video transmission over the Internet faces many difficulties due to its large size. Therefore, to reduce the network bandwidth requirement of 360-degree video, Viewport Adaptive Streaming (VAS) was proposed. An important issue in VAS is how to estimate future user viewing direction. In this paper, we propose an algorithm called GLVP (GRU-LSTM-based-Viewport-Prediction) to estimate the typical view for the VAS system. The results show that our method can improve viewport estimation from 9.5% to near 20%compared with other methods.