Kalman Filter-based Head Motion Prediction for Cloud-based Mixed Reality

被引:22
作者
Guel, Serhan [1 ]
Bosse, Sebastian [1 ]
Podborski, Dimitri [1 ]
Schierl, Thomas [1 ]
Hellge, Cornelius [1 ]
机构
[1] Fraunhofer HHI, Berlin, Germany
来源
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA | 2020年
关键词
volumetric video; augmented reality; mixed reality; cloud-based rendering; head motion prediction; Kalman filter; time series analysis;
D O I
10.1145/3394171.3413699
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Volumetric video allows viewers to experience highly-realistic 3D content with six degrees of freedom in mixed reality (MR) environments. Rendering complex volumetric videos can require a prohibitively high amount of computational power for mobile devices. A promising technique to reduce the computational burden on mobile devices is to perform the rendering at a cloud server. However, cloud-based rendering systems suffer from an increased interaction (motion-to-photon) latency that may cause registration errors in MR environments. One way of reducing the effective latency is to predict the viewer's head pose and render the corresponding view from the volumetric video in advance. In this paper, we design a Kalman filter for head motion prediction in our cloud-based volumetric video streaming system. We analyze the performance of our approach using recorded head motion traces and compare its performance to an autoregression model for different prediction intervals (look-ahead times). Our results show that the Kalman filter can predict head orientations 0.5 degrees more accurately than the autoregression model for a look-ahead time of 60 ms.
引用
收藏
页码:3632 / 3641
页数:10
相关论文
共 54 条
  • [1] MAXIMUM LIKELIHOOD IDENTIFICATION OF GAUSSIAN AUTOREGRESSIVE MOVING AVERAGE MODELS
    AKAIKE, H
    [J]. BIOMETRIKA, 1973, 60 (02) : 255 - 265
  • [2] Your Attention is Unique: Detecting 360-Degree Video Saliency in Head-Mounted Display for Head Movement Prediction
    Anh Nguyen
    Yan, Zhisheng
    Nahrstedt, Klara
    [J]. PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 1190 - 1198
  • [3] [Anonymous], 2017, 2017 INT C 3D IMM IC
  • [4] Azuma R.T., 1995, Proceedings of ACM SIGGRAPH, V95, P401, DOI DOI 10.1145/218380.218496
  • [5] Azuma Ronald Tadao, 1995, THESIS
  • [6] Bao YN, 2016, 2016 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), P1161, DOI 10.1109/BigData.2016.7840720
  • [7] Bar -Shalom Y., 2004, Estimation With Applications To Tracking And Navigation-Theory, Algorithm And Software
  • [8] Beigbeder T., 2004, P ACM NETGAMES, P144
  • [9] Chartrand R, 2011, Int Sch Res Not, V2011, DOI [10.5402/2011/164564, DOI 10.5402/2011/164564]
  • [10] Toward Truly Immersive Holographic-Type Communication: Challenges and Solutions
    Clemm, Alexander
    Vega, Maria Torres
    Ravuri, Hemanth Kumar
    Wauters, Tim
    De Turck, Filip
    [J]. IEEE COMMUNICATIONS MAGAZINE, 2020, 58 (01) : 93 - 99