Client intelligence for adaptive streaming solutions

Research output: Contribution to journalArticleAcademicpeer-review

45 Citations (Scopus)
3 Downloads (Pure)

Abstract

In state-of-the-art adaptive streaming solutions, to cope with varying network conditions, the client side can switch between several video copies encoded at different bit-rates during streaming. Each video copy is divided into chunks of equal duration. To achieve continuous video playback, each chunk needs to arrive at the client before its playback deadline. The perceptual quality of a chunk increases with the chunk size in bits, whereas bigger chunks require more transmission time and, as a result, have a higher risk of missing transmission deadline. Therefore, there is a trade-off between the overall video quality and continuous playback, which can be optimized by proper selection of the next chunk from the encoded versions. This paper proposes a method to compute a set of optimal client strategies for this purpose.
Original languageEnglish
Pages (from-to)378-389
JournalSignal Processing : Image Communication
Volume26
Issue number7
DOIs
Publication statusPublished - 2011

Fingerprint

Switches

Cite this

@article{93c6747bf87a4205a267b68f1b936d15,
title = "Client intelligence for adaptive streaming solutions",
abstract = "In state-of-the-art adaptive streaming solutions, to cope with varying network conditions, the client side can switch between several video copies encoded at different bit-rates during streaming. Each video copy is divided into chunks of equal duration. To achieve continuous video playback, each chunk needs to arrive at the client before its playback deadline. The perceptual quality of a chunk increases with the chunk size in bits, whereas bigger chunks require more transmission time and, as a result, have a higher risk of missing transmission deadline. Therefore, there is a trade-off between the overall video quality and continuous playback, which can be optimized by proper selection of the next chunk from the encoded versions. This paper proposes a method to compute a set of optimal client strategies for this purpose.",
author = "D.S. Jarnikov and T. Ozcelebi",
year = "2011",
doi = "10.1016/j.image.2011.03.003",
language = "English",
volume = "26",
pages = "378--389",
journal = "Signal Processing : Image Communication",
issn = "0923-5965",
publisher = "Elsevier",
number = "7",

}

Client intelligence for adaptive streaming solutions. / Jarnikov, D.S.; Ozcelebi, T.

In: Signal Processing : Image Communication, Vol. 26, No. 7, 2011, p. 378-389.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Client intelligence for adaptive streaming solutions

AU - Jarnikov, D.S.

AU - Ozcelebi, T.

PY - 2011

Y1 - 2011

N2 - In state-of-the-art adaptive streaming solutions, to cope with varying network conditions, the client side can switch between several video copies encoded at different bit-rates during streaming. Each video copy is divided into chunks of equal duration. To achieve continuous video playback, each chunk needs to arrive at the client before its playback deadline. The perceptual quality of a chunk increases with the chunk size in bits, whereas bigger chunks require more transmission time and, as a result, have a higher risk of missing transmission deadline. Therefore, there is a trade-off between the overall video quality and continuous playback, which can be optimized by proper selection of the next chunk from the encoded versions. This paper proposes a method to compute a set of optimal client strategies for this purpose.

AB - In state-of-the-art adaptive streaming solutions, to cope with varying network conditions, the client side can switch between several video copies encoded at different bit-rates during streaming. Each video copy is divided into chunks of equal duration. To achieve continuous video playback, each chunk needs to arrive at the client before its playback deadline. The perceptual quality of a chunk increases with the chunk size in bits, whereas bigger chunks require more transmission time and, as a result, have a higher risk of missing transmission deadline. Therefore, there is a trade-off between the overall video quality and continuous playback, which can be optimized by proper selection of the next chunk from the encoded versions. This paper proposes a method to compute a set of optimal client strategies for this purpose.

U2 - 10.1016/j.image.2011.03.003

DO - 10.1016/j.image.2011.03.003

M3 - Article

VL - 26

SP - 378

EP - 389

JO - Signal Processing : Image Communication

JF - Signal Processing : Image Communication

SN - 0923-5965

IS - 7

ER -