Complexity modeling for coarse grain scalable (CGS) video decoding

Chun Yen Yu, Wei Hsiang Chiu, Chih-Hung Kuo

Research output: Contribution to conferencePaper

Abstract

This paper proposes a hybrid model to predict CGS-SVC decoding complexity. We take advantage of both the statistic characteristic of complexity features and linear relationship between quality layers to model the complexity. Experimental results show that the proposed method provides a good prediction accuracy for all quality layer. The whole average prediction error of test sequences is 1.51% approximately. Furthermore, the target platform can decode the suitable quality layer by our layer decision mechanism and an accurate prediction result.

Original languageEnglish
Pages42-45
Number of pages4
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013 - Chengdu, China
Duration: 2013 Nov 152013 Nov 17

Other

Other2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013
CountryChina
CityChengdu
Period13-11-1513-11-17

Fingerprint

Decoding
Statistics

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Yu, C. Y., Chiu, W. H., & Kuo, C-H. (2013). Complexity modeling for coarse grain scalable (CGS) video decoding. 42-45. Paper presented at 2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013, Chengdu, China. https://doi.org/10.1109/ICCCAS.2013.6765182
Yu, Chun Yen ; Chiu, Wei Hsiang ; Kuo, Chih-Hung. / Complexity modeling for coarse grain scalable (CGS) video decoding. Paper presented at 2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013, Chengdu, China.4 p.
@conference{a7cbdc20c1ba4d3286f0b4704ac2057c,
title = "Complexity modeling for coarse grain scalable (CGS) video decoding",
abstract = "This paper proposes a hybrid model to predict CGS-SVC decoding complexity. We take advantage of both the statistic characteristic of complexity features and linear relationship between quality layers to model the complexity. Experimental results show that the proposed method provides a good prediction accuracy for all quality layer. The whole average prediction error of test sequences is 1.51{\%} approximately. Furthermore, the target platform can decode the suitable quality layer by our layer decision mechanism and an accurate prediction result.",
author = "Yu, {Chun Yen} and Chiu, {Wei Hsiang} and Chih-Hung Kuo",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/ICCCAS.2013.6765182",
language = "English",
pages = "42--45",
note = "2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013 ; Conference date: 15-11-2013 Through 17-11-2013",

}

Yu, CY, Chiu, WH & Kuo, C-H 2013, 'Complexity modeling for coarse grain scalable (CGS) video decoding' Paper presented at 2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013, Chengdu, China, 13-11-15 - 13-11-17, pp. 42-45. https://doi.org/10.1109/ICCCAS.2013.6765182

Complexity modeling for coarse grain scalable (CGS) video decoding. / Yu, Chun Yen; Chiu, Wei Hsiang; Kuo, Chih-Hung.

2013. 42-45 Paper presented at 2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013, Chengdu, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Complexity modeling for coarse grain scalable (CGS) video decoding

AU - Yu, Chun Yen

AU - Chiu, Wei Hsiang

AU - Kuo, Chih-Hung

PY - 2013/1/1

Y1 - 2013/1/1

N2 - This paper proposes a hybrid model to predict CGS-SVC decoding complexity. We take advantage of both the statistic characteristic of complexity features and linear relationship between quality layers to model the complexity. Experimental results show that the proposed method provides a good prediction accuracy for all quality layer. The whole average prediction error of test sequences is 1.51% approximately. Furthermore, the target platform can decode the suitable quality layer by our layer decision mechanism and an accurate prediction result.

AB - This paper proposes a hybrid model to predict CGS-SVC decoding complexity. We take advantage of both the statistic characteristic of complexity features and linear relationship between quality layers to model the complexity. Experimental results show that the proposed method provides a good prediction accuracy for all quality layer. The whole average prediction error of test sequences is 1.51% approximately. Furthermore, the target platform can decode the suitable quality layer by our layer decision mechanism and an accurate prediction result.

UR - http://www.scopus.com/inward/record.url?scp=84898828036&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898828036&partnerID=8YFLogxK

U2 - 10.1109/ICCCAS.2013.6765182

DO - 10.1109/ICCCAS.2013.6765182

M3 - Paper

AN - SCOPUS:84898828036

SP - 42

EP - 45

ER -

Yu CY, Chiu WH, Kuo C-H. Complexity modeling for coarse grain scalable (CGS) video decoding. 2013. Paper presented at 2013 International Conference on Communications, Circuits and Systems, ICCCAS 2013, Chengdu, China. https://doi.org/10.1109/ICCCAS.2013.6765182