Perceptual Quality Driven Adaptive Video Coding Using JND Estimation

Masaru Takeuchi, Shintaro Saika, Yusuke Sakamoto, Tatsuya Nagashima, Zhengxue Cheng, Kenji Kanai, Jiro Katto, Kaijin Wei, Ju Zengwei, Xu Wei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We introduce a perceptual video quality driven video encoding solution for optimized adaptive streaming. By using multiple bitrate/resolution encoding like MPEG-DASH, video streaming services can deliver the best video stream to a client, under the conditions of the client's available bandwidth and viewing device capability. However, conventional fixed encoding recipes (i.e., resolution-bitrate pairs) suffer from many problems, such as improper resolution selection and stream redundancy. To avoid these problems, we propose a novel video coding method, which generates multiple representations with constant JustNoticeable Difference (JND) interval. For this purpose, we developed a JND scale estimator using Support Vector Regression (SVR), and designed a pre-encoder which outputs an encoding recipe with constant JND interval in an adaptive manner to input video.

Original languageEnglish
Title of host publication2018 Picture Coding Symposium, PCS 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages179-183
Number of pages5
ISBN (Print)9781538641606
DOIs
Publication statusPublished - 2018 Sep 5
Event33rd Picture Coding Symposium, PCS 2018 - San Francisco, United States
Duration: 2018 Jun 242018 Jun 27

Other

Other33rd Picture Coding Symposium, PCS 2018
CountryUnited States
CitySan Francisco
Period18/6/2418/6/27

Fingerprint

Video streaming
Image coding
Redundancy
Bandwidth

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Cite this

Takeuchi, M., Saika, S., Sakamoto, Y., Nagashima, T., Cheng, Z., Kanai, K., ... Wei, X. (2018). Perceptual Quality Driven Adaptive Video Coding Using JND Estimation. In 2018 Picture Coding Symposium, PCS 2018 - Proceedings (pp. 179-183). [8456297] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PCS.2018.8456297

Perceptual Quality Driven Adaptive Video Coding Using JND Estimation. / Takeuchi, Masaru; Saika, Shintaro; Sakamoto, Yusuke; Nagashima, Tatsuya; Cheng, Zhengxue; Kanai, Kenji; Katto, Jiro; Wei, Kaijin; Zengwei, Ju; Wei, Xu.

2018 Picture Coding Symposium, PCS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 179-183 8456297.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Takeuchi, M, Saika, S, Sakamoto, Y, Nagashima, T, Cheng, Z, Kanai, K, Katto, J, Wei, K, Zengwei, J & Wei, X 2018, Perceptual Quality Driven Adaptive Video Coding Using JND Estimation. in 2018 Picture Coding Symposium, PCS 2018 - Proceedings., 8456297, Institute of Electrical and Electronics Engineers Inc., pp. 179-183, 33rd Picture Coding Symposium, PCS 2018, San Francisco, United States, 18/6/24. https://doi.org/10.1109/PCS.2018.8456297
Takeuchi M, Saika S, Sakamoto Y, Nagashima T, Cheng Z, Kanai K et al. Perceptual Quality Driven Adaptive Video Coding Using JND Estimation. In 2018 Picture Coding Symposium, PCS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 179-183. 8456297 https://doi.org/10.1109/PCS.2018.8456297
Takeuchi, Masaru ; Saika, Shintaro ; Sakamoto, Yusuke ; Nagashima, Tatsuya ; Cheng, Zhengxue ; Kanai, Kenji ; Katto, Jiro ; Wei, Kaijin ; Zengwei, Ju ; Wei, Xu. / Perceptual Quality Driven Adaptive Video Coding Using JND Estimation. 2018 Picture Coding Symposium, PCS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 179-183
@inproceedings{62c3ecad3f10480bbde7a61b21cfbbed,
title = "Perceptual Quality Driven Adaptive Video Coding Using JND Estimation",
abstract = "We introduce a perceptual video quality driven video encoding solution for optimized adaptive streaming. By using multiple bitrate/resolution encoding like MPEG-DASH, video streaming services can deliver the best video stream to a client, under the conditions of the client's available bandwidth and viewing device capability. However, conventional fixed encoding recipes (i.e., resolution-bitrate pairs) suffer from many problems, such as improper resolution selection and stream redundancy. To avoid these problems, we propose a novel video coding method, which generates multiple representations with constant JustNoticeable Difference (JND) interval. For this purpose, we developed a JND scale estimator using Support Vector Regression (SVR), and designed a pre-encoder which outputs an encoding recipe with constant JND interval in an adaptive manner to input video.",
author = "Masaru Takeuchi and Shintaro Saika and Yusuke Sakamoto and Tatsuya Nagashima and Zhengxue Cheng and Kenji Kanai and Jiro Katto and Kaijin Wei and Ju Zengwei and Xu Wei",
year = "2018",
month = "9",
day = "5",
doi = "10.1109/PCS.2018.8456297",
language = "English",
isbn = "9781538641606",
pages = "179--183",
booktitle = "2018 Picture Coding Symposium, PCS 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Perceptual Quality Driven Adaptive Video Coding Using JND Estimation

AU - Takeuchi, Masaru

AU - Saika, Shintaro

AU - Sakamoto, Yusuke

AU - Nagashima, Tatsuya

AU - Cheng, Zhengxue

AU - Kanai, Kenji

AU - Katto, Jiro

AU - Wei, Kaijin

AU - Zengwei, Ju

AU - Wei, Xu

PY - 2018/9/5

Y1 - 2018/9/5

N2 - We introduce a perceptual video quality driven video encoding solution for optimized adaptive streaming. By using multiple bitrate/resolution encoding like MPEG-DASH, video streaming services can deliver the best video stream to a client, under the conditions of the client's available bandwidth and viewing device capability. However, conventional fixed encoding recipes (i.e., resolution-bitrate pairs) suffer from many problems, such as improper resolution selection and stream redundancy. To avoid these problems, we propose a novel video coding method, which generates multiple representations with constant JustNoticeable Difference (JND) interval. For this purpose, we developed a JND scale estimator using Support Vector Regression (SVR), and designed a pre-encoder which outputs an encoding recipe with constant JND interval in an adaptive manner to input video.

AB - We introduce a perceptual video quality driven video encoding solution for optimized adaptive streaming. By using multiple bitrate/resolution encoding like MPEG-DASH, video streaming services can deliver the best video stream to a client, under the conditions of the client's available bandwidth and viewing device capability. However, conventional fixed encoding recipes (i.e., resolution-bitrate pairs) suffer from many problems, such as improper resolution selection and stream redundancy. To avoid these problems, we propose a novel video coding method, which generates multiple representations with constant JustNoticeable Difference (JND) interval. For this purpose, we developed a JND scale estimator using Support Vector Regression (SVR), and designed a pre-encoder which outputs an encoding recipe with constant JND interval in an adaptive manner to input video.

UR - http://www.scopus.com/inward/record.url?scp=85053925636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053925636&partnerID=8YFLogxK

U2 - 10.1109/PCS.2018.8456297

DO - 10.1109/PCS.2018.8456297

M3 - Conference contribution

AN - SCOPUS:85053925636

SN - 9781538641606

SP - 179

EP - 183

BT - 2018 Picture Coding Symposium, PCS 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -