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
Vues en texte intégral
114
Dans cet article, un modèle d'estimation de la qualité basé sur les métadonnées est proposé pour les services de streaming vidéo omnidirectionnels basés sur des tuiles, visant à réaliser une surveillance de la qualité pendant la fourniture du service. Dans les services de streaming vidéo omnidirectionnel (ODV) basés sur des mosaïques, l'ODV est divisé en mosaïques, et les mosaïques de haute qualité et les mosaïques de faible qualité sont distribuées conformément à la direction de visualisation de l'utilisateur. Lorsque l'utilisateur change la direction de visualisation, l'utilisateur regarde temporairement la vidéo avec les tuiles de faible qualité. De plus, plus le temps (délai) jusqu'au téléchargement de la vignette de haute qualité pour la nouvelle direction de visualisation est long, plus le temps de visionnage de la vidéo avec la vignette de faible qualité est long, et donc le temps de retard affecte la qualité. D'après ce qui précède, la qualité vidéo des tuiles de faible qualité et le temps de retard ont un impact significatif sur la qualité, et ces facteurs doivent être pris en compte dans le modèle d'estimation de la qualité. Nous développons des modèles d'estimation de qualité en étendant les modèles d'estimation de qualité conventionnels pour le streaming adaptatif 2D. Nous montrons également que le modèle d'estimation de la qualité utilisant le débit binaire, la résolution et la fréquence d'images des tuiles de haute et basse qualité et que le temps de retard a une précision d'estimation suffisante sur la base des résultats d'expériences d'évaluation subjective de la qualité.
Yuichiro URATA
NTT Corporation
Masanori KOIKE
NTT Corporation
Kazuhisa YAMAGISHI
NTT Corporation
Noritsugu EGI
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.
Copier
Yuichiro URATA, Masanori KOIKE, Kazuhisa YAMAGISHI, Noritsugu EGI, "Metadata-Based Quality-Estimation Model for Tile-Based Omnidirectional Video Streaming" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 5, pp. 478-488, May 2023, doi: 10.1587/transcom.2022EBP3109.
Abstract: In this paper, a metadata-based quality-estimation model is proposed for tile-based omnidirectional video streaming services, aiming to realize quality monitoring during service provision. In the tile-based omnidirectional video (ODV) streaming services, the ODV is divided into tiles, and the high-quality tiles and the low-quality tiles are distributed in accordance with the user's viewing direction. When the user changes the viewing direction, the user temporarily watches video with the low-quality tiles. In addition, the longer the time (delay time) until the high-quality tile for the new viewing direction is downloaded, the longer the viewing time of video with the low-quality tile, and thus the delay time affects quality. From the above, the video quality of the low-quality tiles and the delay time significantly impact quality, and these factors need to be considered in the quality-estimation model. We develop quality-estimation models by extending the conventional quality-estimation models for 2D adaptive streaming. We also show that the quality-estimation model using the bitrate, resolution, and frame rate of high- and low-quality tiles and that the delay time has sufficient estimation accuracy based on the results of subjective quality evaluation experiments.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBP3109/_p
Copier
@ARTICLE{e106-b_5_478,
author={Yuichiro URATA, Masanori KOIKE, Kazuhisa YAMAGISHI, Noritsugu EGI, },
journal={IEICE TRANSACTIONS on Communications},
title={Metadata-Based Quality-Estimation Model for Tile-Based Omnidirectional Video Streaming},
year={2023},
volume={E106-B},
number={5},
pages={478-488},
abstract={In this paper, a metadata-based quality-estimation model is proposed for tile-based omnidirectional video streaming services, aiming to realize quality monitoring during service provision. In the tile-based omnidirectional video (ODV) streaming services, the ODV is divided into tiles, and the high-quality tiles and the low-quality tiles are distributed in accordance with the user's viewing direction. When the user changes the viewing direction, the user temporarily watches video with the low-quality tiles. In addition, the longer the time (delay time) until the high-quality tile for the new viewing direction is downloaded, the longer the viewing time of video with the low-quality tile, and thus the delay time affects quality. From the above, the video quality of the low-quality tiles and the delay time significantly impact quality, and these factors need to be considered in the quality-estimation model. We develop quality-estimation models by extending the conventional quality-estimation models for 2D adaptive streaming. We also show that the quality-estimation model using the bitrate, resolution, and frame rate of high- and low-quality tiles and that the delay time has sufficient estimation accuracy based on the results of subjective quality evaluation experiments.},
keywords={},
doi={10.1587/transcom.2022EBP3109},
ISSN={1745-1345},
month={May},}
Copier
TY - JOUR
TI - Metadata-Based Quality-Estimation Model for Tile-Based Omnidirectional Video Streaming
T2 - IEICE TRANSACTIONS on Communications
SP - 478
EP - 488
AU - Yuichiro URATA
AU - Masanori KOIKE
AU - Kazuhisa YAMAGISHI
AU - Noritsugu EGI
PY - 2023
DO - 10.1587/transcom.2022EBP3109
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 5
JA - IEICE TRANSACTIONS on Communications
Y1 - May 2023
AB - In this paper, a metadata-based quality-estimation model is proposed for tile-based omnidirectional video streaming services, aiming to realize quality monitoring during service provision. In the tile-based omnidirectional video (ODV) streaming services, the ODV is divided into tiles, and the high-quality tiles and the low-quality tiles are distributed in accordance with the user's viewing direction. When the user changes the viewing direction, the user temporarily watches video with the low-quality tiles. In addition, the longer the time (delay time) until the high-quality tile for the new viewing direction is downloaded, the longer the viewing time of video with the low-quality tile, and thus the delay time affects quality. From the above, the video quality of the low-quality tiles and the delay time significantly impact quality, and these factors need to be considered in the quality-estimation model. We develop quality-estimation models by extending the conventional quality-estimation models for 2D adaptive streaming. We also show that the quality-estimation model using the bitrate, resolution, and frame rate of high- and low-quality tiles and that the delay time has sufficient estimation accuracy based on the results of subjective quality evaluation experiments.
ER -