Perceptual Evaluation on Audio-visual Dataset of 360 Content

Randy Frans Fela; Andréas Pastor; Patrick Le Callet; Nick Zacharov; Toinon Vigier; Søren Forchhammer

doi:10.1109/ICMEW56448.2022.9859426

Perceptual Evaluation on Audio-visual Dataset of 360 Content

Randy Frans Fela, Andréas Pastor, Patrick Le Callet, Nick Zacharov^*, Toinon Vigier, Søren Forchhammer

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

79 Downloads (Pure)

Abstract

To open up new possibilities to assess the multimodal perceptual quality of omnidirectional media formats, we proposed a novel open source 360 audiovisual (AV) quality dataset. The dataset consists of high-quality 360 video clips in equirectangular (ERP) format and higher-order ambisonic (4th order) along with the subjective scores. Three subjective quality experiments were conducted for audio, video, and AV with the procedures detailed in this paper. Using the data from subjective tests, we demonstrated that this dataset can be used to quantify perceived audio, video, and audiovisual quality. The diversity and discriminability of subjective scores were also analyzed. Finally, we investigated how our dataset correlates with various objective quality metrics of audio and video. Evidence from the results of this study implies that the proposed dataset can benefit
future studies on multimodal quality evaluation of 360 content.

Original language	English
Title of host publication	Proceedings of IEEE International Conference on Multimedia & Expo
Number of pages	6
Publisher	IEEE
Publication date	2022
ISBN (Print)	978-1-6654-7219-7
DOIs	https://doi.org/10.1109/ICMEW56448.2022.9859426
Publication status	Published - 2022
Event	2022 IEEE International Conference on Multimedia and Expo - Taipei International Convention Center, Taipei, Taiwan, Province of China Duration: 18 Jul 2022 → 22 Jul 2022 https://2022.ieeeicme.org/

Conference

Conference	2022 IEEE International Conference on Multimedia and Expo
Location	Taipei International Convention Center
Country/Territory	Taiwan, Province of China
City	Taipei
Period	18/07/2022 → 22/07/2022
Sponsor	Chinese Academy of Sciences, IEEE, IEEE, IEEE Communications Society, IEEE
Internet address	https://2022.ieeeicme.org/

Keywords

Omnidirectional media format
Audiovisual dataset
360 video
Ambisonics
Quality evaluation

Access to Document

10.1109/ICMEW56448.2022.9859426

FulltextSubmitted manuscript, 4.45 MB

OpenUrl availability

Full text

Cite this

@inproceedings{1bccd3ce75a6496eb0ade6d73d27446e,

title = "Perceptual Evaluation on Audio-visual Dataset of 360 Content",

abstract = "To open up new possibilities to assess the multimodal perceptual quality of omnidirectional media formats, we proposed a novel open source 360 audiovisual (AV) quality dataset. The dataset consists of high-quality 360 video clips in equirectangular (ERP) format and higher-order ambisonic (4th order) along with the subjective scores. Three subjective quality experiments were conducted for audio, video, and AV with the procedures detailed in this paper. Using the data from subjective tests, we demonstrated that this dataset can be used to quantify perceived audio, video, and audiovisual quality. The diversity and discriminability of subjective scores were also analyzed. Finally, we investigated how our dataset correlates with various objective quality metrics of audio and video. Evidence from the results of this study implies that the proposed dataset can benefitfuture studies on multimodal quality evaluation of 360 content.",

keywords = "Omnidirectional media format, Audiovisual dataset, 360 video, Ambisonics, Quality evaluation",

author = "Fela, {Randy Frans} and Andr{\'e}as Pastor and {Le Callet}, Patrick and Nick Zacharov and Toinon Vigier and S{\o}ren Forchhammer",

year = "2022",

doi = "10.1109/ICMEW56448.2022.9859426",

language = "English",

isbn = "978-1-6654-7219-7",

booktitle = "Proceedings of IEEE International Conference on Multimedia & Expo",

publisher = "IEEE",

address = "United States",

note = "2022 IEEE International Conference on Multimedia and Expo, ICME 2022 ; Conference date: 18-07-2022 Through 22-07-2022",

url = "https://2022.ieeeicme.org/",

}

Fela, RF, Pastor, A, Le Callet, P, Zacharov, N, Vigier, T & Forchhammer, S 2022, Perceptual Evaluation on Audio-visual Dataset of 360 Content. in Proceedings of IEEE International Conference on Multimedia & Expo. IEEE, 2022 IEEE International Conference on Multimedia and Expo, Taipei, Taiwan, Province of China, 18/07/2022. https://doi.org/10.1109/ICMEW56448.2022.9859426

TY - GEN

T1 - Perceptual Evaluation on Audio-visual Dataset of 360 Content

AU - Fela, Randy Frans

AU - Pastor, Andréas

AU - Le Callet, Patrick

AU - Zacharov, Nick

AU - Vigier, Toinon

AU - Forchhammer, Søren

PY - 2022

Y1 - 2022

N2 - To open up new possibilities to assess the multimodal perceptual quality of omnidirectional media formats, we proposed a novel open source 360 audiovisual (AV) quality dataset. The dataset consists of high-quality 360 video clips in equirectangular (ERP) format and higher-order ambisonic (4th order) along with the subjective scores. Three subjective quality experiments were conducted for audio, video, and AV with the procedures detailed in this paper. Using the data from subjective tests, we demonstrated that this dataset can be used to quantify perceived audio, video, and audiovisual quality. The diversity and discriminability of subjective scores were also analyzed. Finally, we investigated how our dataset correlates with various objective quality metrics of audio and video. Evidence from the results of this study implies that the proposed dataset can benefitfuture studies on multimodal quality evaluation of 360 content.

AB - To open up new possibilities to assess the multimodal perceptual quality of omnidirectional media formats, we proposed a novel open source 360 audiovisual (AV) quality dataset. The dataset consists of high-quality 360 video clips in equirectangular (ERP) format and higher-order ambisonic (4th order) along with the subjective scores. Three subjective quality experiments were conducted for audio, video, and AV with the procedures detailed in this paper. Using the data from subjective tests, we demonstrated that this dataset can be used to quantify perceived audio, video, and audiovisual quality. The diversity and discriminability of subjective scores were also analyzed. Finally, we investigated how our dataset correlates with various objective quality metrics of audio and video. Evidence from the results of this study implies that the proposed dataset can benefitfuture studies on multimodal quality evaluation of 360 content.

KW - Omnidirectional media format

KW - Audiovisual dataset

KW - 360 video

KW - Ambisonics

KW - Quality evaluation

U2 - 10.1109/ICMEW56448.2022.9859426

DO - 10.1109/ICMEW56448.2022.9859426

M3 - Article in proceedings

SN - 978-1-6654-7219-7

BT - Proceedings of IEEE International Conference on Multimedia & Expo

PB - IEEE

T2 - 2022 IEEE International Conference on Multimedia and Expo

Y2 - 18 July 2022 through 22 July 2022

ER -

Perceptual Evaluation on Audio-visual Dataset of 360 Content

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this