The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Exibições de texto completo
99
Como a qualidade dos serviços de streaming de vídeo é degradada devido à codificação, ao congestionamento da rede e à falta de buffer de playout, a normalidade dos serviços precisa ser monitorada através da coleta da qualidade medida nos clientes finais. Ao medir a qualidade nos clientes finais, o poder computacional deve ser suficientemente baixo, as informações do fluxo de bits não podem ser acessadas para a estimativa da qualidade devido à criptografia e o vídeo de referência não pode ser usado nos clientes finais. Portanto, modelos baseados em metadados foram desenvolvidos e padronizados que usam metadados como resolução, taxa de quadros e taxa de bits e informações de travamento como entrada e calculam a qualidade. No entanto, a qualidade calculada para serviços de TV linear e vídeo sob demanda (VoD) não pode ser comparada porque os modelos baseados em metadados não podem calcular os impactos das estratégias de codec (por exemplo, H.264/AVC, H.265/HEVC e AV1) e configurações (por exemplo, codificação de 1 passagem para TV linear ou codificação de 2 passagens para VoD) na qualidade. Para levar em conta o impacto das estratégias e configurações do codec, os coeficientes do modelo baseado em metadados precisam ser otimizados por estratégia e configuração do codec usando qualidade subjetiva. No entanto, testes extensos de avaliação subjetiva são difíceis de realizar frequentemente porque são caros e demorados e precisam ser conduzidos por especialistas em qualidade de vídeo. Portanto, para monitorar a qualidade de diversos tipos de serviços de streaming de vídeo (por exemplo, TV linear e VoD) e comparar essas qualidades, é proposto um procedimento de derivação para obtenção de coeficientes de modelos baseados em metadados utilizando um modelo de referência completa. Para validar o procedimento, foram realizados extensos testes de avaliação subjetiva. Finalmente, é mostrado que três modelos baseados em metadados (ou seja, o modelo P.1203.1 modo 0, modelo P.1203.1 modo 0 estendido e modelo proposto por Yamagishi et al.) baseados no procedimento proposto usando a fusão de avaliação multimétodo de vídeo (VMAF) estima a qualidade com precisão em termos de erro quadrático médio.
Kazuhisa YAMAGISHI
NTT Corporation
Noritsugu EGI
NTT Corporation
Noriko YOSHIMURA
NTT Corporation
Pierre LEBRETON
NTT Corporation
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Kazuhisa YAMAGISHI, Noritsugu EGI, Noriko YOSHIMURA, Pierre LEBRETON, "Derivation Procedure of Coefficients of Metadata-Based Model for Adaptive Bitrate Streaming Services" in IEICE TRANSACTIONS on Communications,
vol. E104-B, no. 7, pp. 725-737, July 2021, doi: 10.1587/transcom.2020CQP0002.
Abstract: Since the quality of video streaming services is degraded due to the encoding, network congestion, and lack of a playout buffer, the normality of services needs to be monitored by gathering the quality measured at the end clients. When measuring quality at the end clients, the computational power should be sufficiently low, the bitstream information cannot be accessed for the quality estimation due to the encryption, and reference video cannot be used at the end clients. Therefore, metadata-based models have been developed and standardized that take metadata such as the resolution, framerate, and bitrate, and stalling information as input and calculate the quality. However, calculated quality for linear TV and video on demand (VoD) services cannot be compared because metadata-based models cannot calculate the impacts of codec strategies (e.g., H.264/AVC, H.265/HEVC, and AV1) and configurations (e.g., 1-pass encoding for linear TV or 2-pass encoding for VoD) on the quality. To take into account the impact of codec strategies and configurations, coefficients of metadata-based model need to be optimized per codec strategy and configuration using subjective quality. However, extensive subjective assessment tests are difficult to frequently conduct because they are expensive and time consuming and need to be conducted by video quality experts. Therefore, to monitor the quality of several types of video streaming services (e.g., linear TV and VoD) and to compare these qualities, a derivation procedure is proposed for obtaining coefficients of metadata-based models using a full-reference model. To validate the procedure, extensive subjective assessment tests were conducted. Finally, it is shown that three metadata-based models (i.e., the P.1203.1 mode 0 model, extended P.1203.1 mode 0 model, and model proposed by Yamagishi et al.) based on the proposed procedure using the video multimethod assessment fusion (VMAF) algorithm estimate quality accurately in terms of root mean squared error.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2020CQP0002/_p
Copiar
@ARTICLE{e104-b_7_725,
author={Kazuhisa YAMAGISHI, Noritsugu EGI, Noriko YOSHIMURA, Pierre LEBRETON, },
journal={IEICE TRANSACTIONS on Communications},
title={Derivation Procedure of Coefficients of Metadata-Based Model for Adaptive Bitrate Streaming Services},
year={2021},
volume={E104-B},
number={7},
pages={725-737},
abstract={Since the quality of video streaming services is degraded due to the encoding, network congestion, and lack of a playout buffer, the normality of services needs to be monitored by gathering the quality measured at the end clients. When measuring quality at the end clients, the computational power should be sufficiently low, the bitstream information cannot be accessed for the quality estimation due to the encryption, and reference video cannot be used at the end clients. Therefore, metadata-based models have been developed and standardized that take metadata such as the resolution, framerate, and bitrate, and stalling information as input and calculate the quality. However, calculated quality for linear TV and video on demand (VoD) services cannot be compared because metadata-based models cannot calculate the impacts of codec strategies (e.g., H.264/AVC, H.265/HEVC, and AV1) and configurations (e.g., 1-pass encoding for linear TV or 2-pass encoding for VoD) on the quality. To take into account the impact of codec strategies and configurations, coefficients of metadata-based model need to be optimized per codec strategy and configuration using subjective quality. However, extensive subjective assessment tests are difficult to frequently conduct because they are expensive and time consuming and need to be conducted by video quality experts. Therefore, to monitor the quality of several types of video streaming services (e.g., linear TV and VoD) and to compare these qualities, a derivation procedure is proposed for obtaining coefficients of metadata-based models using a full-reference model. To validate the procedure, extensive subjective assessment tests were conducted. Finally, it is shown that three metadata-based models (i.e., the P.1203.1 mode 0 model, extended P.1203.1 mode 0 model, and model proposed by Yamagishi et al.) based on the proposed procedure using the video multimethod assessment fusion (VMAF) algorithm estimate quality accurately in terms of root mean squared error.},
keywords={},
doi={10.1587/transcom.2020CQP0002},
ISSN={1745-1345},
month={July},}
Copiar
TY - JOUR
TI - Derivation Procedure of Coefficients of Metadata-Based Model for Adaptive Bitrate Streaming Services
T2 - IEICE TRANSACTIONS on Communications
SP - 725
EP - 737
AU - Kazuhisa YAMAGISHI
AU - Noritsugu EGI
AU - Noriko YOSHIMURA
AU - Pierre LEBRETON
PY - 2021
DO - 10.1587/transcom.2020CQP0002
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E104-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2021
AB - Since the quality of video streaming services is degraded due to the encoding, network congestion, and lack of a playout buffer, the normality of services needs to be monitored by gathering the quality measured at the end clients. When measuring quality at the end clients, the computational power should be sufficiently low, the bitstream information cannot be accessed for the quality estimation due to the encryption, and reference video cannot be used at the end clients. Therefore, metadata-based models have been developed and standardized that take metadata such as the resolution, framerate, and bitrate, and stalling information as input and calculate the quality. However, calculated quality for linear TV and video on demand (VoD) services cannot be compared because metadata-based models cannot calculate the impacts of codec strategies (e.g., H.264/AVC, H.265/HEVC, and AV1) and configurations (e.g., 1-pass encoding for linear TV or 2-pass encoding for VoD) on the quality. To take into account the impact of codec strategies and configurations, coefficients of metadata-based model need to be optimized per codec strategy and configuration using subjective quality. However, extensive subjective assessment tests are difficult to frequently conduct because they are expensive and time consuming and need to be conducted by video quality experts. Therefore, to monitor the quality of several types of video streaming services (e.g., linear TV and VoD) and to compare these qualities, a derivation procedure is proposed for obtaining coefficients of metadata-based models using a full-reference model. To validate the procedure, extensive subjective assessment tests were conducted. Finally, it is shown that three metadata-based models (i.e., the P.1203.1 mode 0 model, extended P.1203.1 mode 0 model, and model proposed by Yamagishi et al.) based on the proposed procedure using the video multimethod assessment fusion (VMAF) algorithm estimate quality accurately in terms of root mean squared error.
ER -