Non-intrusive Packet-Layer Model for Monitoring Video Quality of IPTV Services
Summary :
Developing a non-intrusive packet-layer model is required to passively monitor the quality of experience (QoE) during service. We propose a packet-layer model that can be used to estimate the video quality of IPTV using quality parameters derived from transmitted packet headers. The computational load of the model is lighter than that of the model that takes video signals and/or video-related bitstream information such as motion vectors as input. This model is applicable even if the transmitted bitstream information is encrypted because it uses transmitted packet headers rather than bitstream information. For developing the model, we conducted three extensive subjective quality assessments for different encoders and decoders (codecs), and video content. Then, we modeled the subjective video quality assessment characteristics based on objective features affected by coding and packet loss. Finally, we verified the model's validity by applying our model to unknown data sets different from training data sets used above.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E92-A No.12 pp.3297-3306
- Publication Date
- 2009/12/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E92.A.3297
- Type of Manuscript
- Special Section PAPER (Special Section on Image Media Quality)
- Category
- Evaluation
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Kazuhisa YAMAGISHI, Takanori HAYASHI, "Non-intrusive Packet-Layer Model for Monitoring Video Quality of IPTV Services" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 12, pp. 3297-3306, December 2009, doi: 10.1587/transfun.E92.A.3297.
Abstract: Developing a non-intrusive packet-layer model is required to passively monitor the quality of experience (QoE) during service. We propose a packet-layer model that can be used to estimate the video quality of IPTV using quality parameters derived from transmitted packet headers. The computational load of the model is lighter than that of the model that takes video signals and/or video-related bitstream information such as motion vectors as input. This model is applicable even if the transmitted bitstream information is encrypted because it uses transmitted packet headers rather than bitstream information. For developing the model, we conducted three extensive subjective quality assessments for different encoders and decoders (codecs), and video content. Then, we modeled the subjective video quality assessment characteristics based on objective features affected by coding and packet loss. Finally, we verified the model's validity by applying our model to unknown data sets different from training data sets used above.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.3297/_p
Copy
@ARTICLE{e92-a_12_3297,
author={Kazuhisa YAMAGISHI, Takanori HAYASHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Non-intrusive Packet-Layer Model for Monitoring Video Quality of IPTV Services},
year={2009},
volume={E92-A},
number={12},
pages={3297-3306},
abstract={Developing a non-intrusive packet-layer model is required to passively monitor the quality of experience (QoE) during service. We propose a packet-layer model that can be used to estimate the video quality of IPTV using quality parameters derived from transmitted packet headers. The computational load of the model is lighter than that of the model that takes video signals and/or video-related bitstream information such as motion vectors as input. This model is applicable even if the transmitted bitstream information is encrypted because it uses transmitted packet headers rather than bitstream information. For developing the model, we conducted three extensive subjective quality assessments for different encoders and decoders (codecs), and video content. Then, we modeled the subjective video quality assessment characteristics based on objective features affected by coding and packet loss. Finally, we verified the model's validity by applying our model to unknown data sets different from training data sets used above.},
keywords={},
doi={10.1587/transfun.E92.A.3297},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - Non-intrusive Packet-Layer Model for Monitoring Video Quality of IPTV Services
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 3297
EP - 3306
AU - Kazuhisa YAMAGISHI
AU - Takanori HAYASHI
PY - 2009
DO - 10.1587/transfun.E92.A.3297
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2009
AB - Developing a non-intrusive packet-layer model is required to passively monitor the quality of experience (QoE) during service. We propose a packet-layer model that can be used to estimate the video quality of IPTV using quality parameters derived from transmitted packet headers. The computational load of the model is lighter than that of the model that takes video signals and/or video-related bitstream information such as motion vectors as input. This model is applicable even if the transmitted bitstream information is encrypted because it uses transmitted packet headers rather than bitstream information. For developing the model, we conducted three extensive subjective quality assessments for different encoders and decoders (codecs), and video content. Then, we modeled the subjective video quality assessment characteristics based on objective features affected by coding and packet loss. Finally, we verified the model's validity by applying our model to unknown data sets different from training data sets used above.
ER -
English
