Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge

Haipeng Zhang; Jie Zhang; Weimiao Feng; Kaigui Bian; Hu Tuo

doi:10.1109/ICME55011.2023.00344

Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge

Haipeng Zhang, Jie Zhang, Weimiao Feng, Kaigui Bian, Hu Tuo

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

1 Citation (SciVal)

68 Downloads (Pure)

Abstract

Audiences cangain an immersive experience watching videos from multiple angles (a.k.a. viewpoints). Free Viewpoint Video (FVV) is developed to enable users to choose their preferred viewpoints during the play of a video. However, users may experience a delay if video frames of the chosen viewpoint cannot be timely loaded, or synthesized from multiple video streams of neighboring viewpoints. To address this problem, we present Edge-FVV, an edge-assisted FVV system that employs edge caches to reduce the delay in streaming the requested FVV from the server to client users. We first analyze the capacity and delay at edge caches when answering FVV requests. Next, we propose two types of machine learning algorithms that allocate the users' requests to appropriate edge caches. Our evaluation shows that two types of proposed algorithms outperform benchmarks by 4.2-7.4% and 4.6-6.8%, respectively, in reducing the delay for FVV requests.

Original language	English
Title of host publication	Proceedings - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023
Place of Publication	U. S. A.
Publisher	IEEE
Pages	2009-2014
Number of pages	6
ISBN (Electronic)	9781665468916
DOIs	https://doi.org/10.1109/ICME55011.2023.00344
Publication status	Published - 14 Jul 2023
Event	2023 IEEE International Conference on Multimedia and Expo, ICME 2023 - Brisbane, Australia Duration: 10 Jul 2023 → 14 Jul 2023

Publication series

Name	Proceedings - IEEE International Conference on Multimedia and Expo
Volume	2023-July
ISSN (Print)	1945-7871
ISSN (Electronic)	1945-788X

Conference

Conference	2023 IEEE International Conference on Multimedia and Expo, ICME 2023
Country/Territory	Australia
City	Brisbane
Period	10/07/23 → 14/07/23

Keywords

Free viewpoint video
resource allocation
virtual view synthesis

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications

Access to Document

10.1109/ICME55011.2023.00344

ICME23_Camera_Ready
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Accepted author manuscript, 5.65 MB

Cite this

Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge. / Zhang, Haipeng; Zhang, Jie; Feng, Weimiao et al.
Proceedings - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023. U. S. A.: IEEE, 2023. p. 2009-2014 (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2023-July).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Zhang, H, Zhang, J, Feng, W, Bian, K & Tuo, H 2023, Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge. in Proceedings - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023. Proceedings - IEEE International Conference on Multimedia and Expo, vol. 2023-July, IEEE, U. S. A., pp. 2009-2014, 2023 IEEE International Conference on Multimedia and Expo, ICME 2023, Brisbane, Australia, 10/07/23. https://doi.org/10.1109/ICME55011.2023.00344

@inproceedings{a79ad459c4de493eae070115ce37c232,

title = "Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge",

abstract = "Audiences cangain an immersive experience watching videos from multiple angles (a.k.a. viewpoints). Free Viewpoint Video (FVV) is developed to enable users to choose their preferred viewpoints during the play of a video. However, users may experience a delay if video frames of the chosen viewpoint cannot be timely loaded, or synthesized from multiple video streams of neighboring viewpoints. To address this problem, we present Edge-FVV, an edge-assisted FVV system that employs edge caches to reduce the delay in streaming the requested FVV from the server to client users. We first analyze the capacity and delay at edge caches when answering FVV requests. Next, we propose two types of machine learning algorithms that allocate the users' requests to appropriate edge caches. Our evaluation shows that two types of proposed algorithms outperform benchmarks by 4.2-7.4% and 4.6-6.8%, respectively, in reducing the delay for FVV requests.",

keywords = "Free viewpoint video, resource allocation, virtual view synthesis",

author = "Haipeng Zhang and Jie Zhang and Weimiao Feng and Kaigui Bian and Hu Tuo",

year = "2023",

month = jul,

day = "14",

doi = "10.1109/ICME55011.2023.00344",

language = "English",

series = "Proceedings - IEEE International Conference on Multimedia and Expo",

publisher = "IEEE",

pages = "2009--2014",

booktitle = "Proceedings - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023",

address = "USA United States",

note = "2023 IEEE International Conference on Multimedia and Expo, ICME 2023 ; Conference date: 10-07-2023 Through 14-07-2023",

}

TY - GEN

T1 - Edge-FVV

T2 - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023

AU - Zhang, Haipeng

AU - Zhang, Jie

AU - Feng, Weimiao

AU - Bian, Kaigui

AU - Tuo, Hu

PY - 2023/7/14

Y1 - 2023/7/14

N2 - Audiences cangain an immersive experience watching videos from multiple angles (a.k.a. viewpoints). Free Viewpoint Video (FVV) is developed to enable users to choose their preferred viewpoints during the play of a video. However, users may experience a delay if video frames of the chosen viewpoint cannot be timely loaded, or synthesized from multiple video streams of neighboring viewpoints. To address this problem, we present Edge-FVV, an edge-assisted FVV system that employs edge caches to reduce the delay in streaming the requested FVV from the server to client users. We first analyze the capacity and delay at edge caches when answering FVV requests. Next, we propose two types of machine learning algorithms that allocate the users' requests to appropriate edge caches. Our evaluation shows that two types of proposed algorithms outperform benchmarks by 4.2-7.4% and 4.6-6.8%, respectively, in reducing the delay for FVV requests.

AB - Audiences cangain an immersive experience watching videos from multiple angles (a.k.a. viewpoints). Free Viewpoint Video (FVV) is developed to enable users to choose their preferred viewpoints during the play of a video. However, users may experience a delay if video frames of the chosen viewpoint cannot be timely loaded, or synthesized from multiple video streams of neighboring viewpoints. To address this problem, we present Edge-FVV, an edge-assisted FVV system that employs edge caches to reduce the delay in streaming the requested FVV from the server to client users. We first analyze the capacity and delay at edge caches when answering FVV requests. Next, we propose two types of machine learning algorithms that allocate the users' requests to appropriate edge caches. Our evaluation shows that two types of proposed algorithms outperform benchmarks by 4.2-7.4% and 4.6-6.8%, respectively, in reducing the delay for FVV requests.

KW - Free viewpoint video

KW - resource allocation

KW - virtual view synthesis

UR - http://www.scopus.com/inward/record.url?scp=85171136451&partnerID=8YFLogxK

U2 - 10.1109/ICME55011.2023.00344

DO - 10.1109/ICME55011.2023.00344

M3 - Chapter in a published conference proceeding

AN - SCOPUS:85171136451

T3 - Proceedings - IEEE International Conference on Multimedia and Expo

SP - 2009

EP - 2014

BT - Proceedings - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023

PB - IEEE

CY - U. S. A.

Y2 - 10 July 2023 through 14 July 2023

ER -

Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Logistics Optimisation After Brexit and COVID-19

Cite this

Edge-FVV: Free Viewpoint Video Streaming by Learning at the Edge

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Projects

Logistics Optimisation After Brexit and COVID-19

Cite this