arrow
返回

Graph Learning Based Head Movement Prediction for Interactive 360 Video Streaming

delete2021-01-01
delete13
PRE
AI
X
Xue Zhang
G
Gene Cheung *
赵耀 (Yao Zhao)
P
Patrick Le Callet
林春雨 (Chunyu Lin)
J
Jack Z. G. Tan
DOI:10.1109/TIP.2021.3073283delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Ultra-high definition (UHD) 360 videos encoded in fine quality are typically too large to stream in its entirety over bandwidth (BW)-constrained networks. One popular approach is to interactively extract and send a spatial sub-region corresponding to a viewer's current field-of-view (FoV) in a head-mounted display (HMD) for more BW-efficient streaming. Due to the non-negligible round-trip-time (RTT) delay between server and client, accurate head movement prediction foretelling a viewer's future FoVs is essential. In this paper, we cast the head movement prediction task as a sparse directed graph learning problem: three sources of relevant information-collected viewers' head movement traces, a 360 image saliency map, and a biological human head model-are distilled into a view transition Markov model. Specifically, we formulate a constrained maximum a posteriori (MAP) problem with likelihood and prior terms defined using the three information sources. We solve the MAP problem alternately using a hybrid iterative reweighted least square (IRLS) and Frank-Wolfe (FW) optimization strategy. In each FW iteration, a linear program (LP) is solved, whose runtime is reduced thanks to warm start initialization. Having estimated a Markov model from data, we employ it to optimize a tile-based 360 video streaming system. Extensive experiments show that our head movement prediction scheme noticeably outperformed existing proposals, and our optimized tile-based streaming scheme outperformed competitors in rate-distortion performance.
Keyword:
Head
Streaming media
Predictive models
Data models
Optimization
Directed graphs
Servers
360 video streaming
directed graph learning
head movement prediction
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

B
Beijing Jiaotong University
学者数:
2.2W
论文数: 1.7W
被引数: 1.2W
N
nantes universite
学者数:
1.7W
论文数: 1.2W
被引数: 125
Y
york university - canada
学者数:
8.3K
论文数: 9.0K
被引数: 10
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
The Prediction of Saliency Map for Head and Eye Movements in 360 Degree Images
err2020-09-01
err58
PREAI
errZhu, Yucheng; Zhai, Guangtao; Min, Xiongkuo; Zhou, Jiantao
err分享
err收藏
err分享
err收藏
How is Gaze Influenced by Image Transformations? Dataset and Model
err2020-01-01
err70
errOAAI
errChe, Zhaohui; Borji, Ali; Zhai, Guangtao; Min, Xiongkuo; Guo, Guodong; Le Callet, Patrick
err分享
err收藏
Iteratively Reweighted Least Squares Minimization for Sparse Recovery
err2009-10-19
err1.0K
errOAAI
errDaubechies, Ingrid; Devore, Ronald; Fornasier, Massimo; Guentuerk, C. Sinan
err分享
err收藏
Toronto Lunar Declaration 2005
err2008-07-01
err0
PREAI
errB.H. Foing; R. Richards; C. Sallaberger
err分享
err收藏
学者 查看更多内容