Exploiting NFV techniques towards future VQA methods
Abstract
This paper introduces a novel approximation of the widely used full reference SSIM metric, ideal for the in-network assessment of QoE for multimedia streams. The QoE estimation approximation algorithm has been implemented as a Virtualised Network Function (VNF) in order to be deployed over Network Function Virtualisation (NFV) infrastructures. The proposed method is based on a two steps evaluation process, making use of a test pattern as an intermediate reference according to which the quality of the original and degraded signal is estimated and expands the applicability of SSIM as a reduced reference metric. For the evaluation of the proposed method as a VNF, a laboratory-scale prototype NFV infrastructure was used, supporting dynamic steering of selected video flows towards the proposed nQoEe estimator VNF via an SDN Control Plane application using OpenFlow protocol for the communication with the physical and virtual switches. The evaluation results validate the efficiency of the proposed method as a VNF, in addition the reported accuracy of the proposed method is proven as satisfactory with an average estimation error of 5%.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Improving network management with software defined networking
Kim, H., & Feamster, N. (2013) · IEEE Communications Magazine · doi:10.1109/mcom.2013.6461195 · Cited by 1,271 · see citing works
Reduced-Reference Image Quality Assessment by Structural Similarity Estimation
Rehman, A., & Wang, Z. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2197011 · Cited by 272 · see citing works
OpenFlow-Based Segment Protection in Ethernet Networks
Sgambelluri, A., Giorgetti, A., Cugini, F., Paolucci, F., & Castoldi, P. (2013) · Journal of Optical Communications and Networking · doi:10.1364/jocn.5.001066 · Cited by 194 · see citing works
Assessing Quality of Experience of IPTV and Video on Demand Services in Real-Life Environments
Staelens, N., Moens, S., den Broeck, W. V., Mariën, I., Vermeulen, B., Lambert, P., Rik Van De Walle, B., & Demeester, P. (2010) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2010.2067710 · Cited by 166 · see citing works
A reduced-reference structural similarity approximation for videos corrupted by channel errors
Tagliasacchi, M., Valenzise, G., Naccari, M., et al. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0473-7 · Cited by 21 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
QoE Management of Multimedia Streaming Services in Future Networks: A Tutorial and Survey
Barakabitze, A. A., Barman, N., Ahmad, A., Zadtootaghaj, S., Sun, L., Martini, M. G., & Atzori, L. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2958784 · Cited by 239 · see citing works
- Authors
- Kourtis, M.-A., Liberal, F., Koumaras, H., Xilouris, G., & Trouva, E.
- Affiliations
- University of the Basque Country (ES)
- National Centre of Scientific Research "Demokritos" (GR)
- Venue
- 2017 IEEE 22nd International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)
- Publisher
- IEEE
- Published
- 2017-06
- Pages
- 1-5
- OpenAlex
- W2754965727
- Cited by
- 4
- References
- 5
- Citations by year
- 2023: 2 · 2021: 1 · 2019: 1
- FWCI
- 0.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD) (publishedVersion)
- Funders
- Horizon 2020 Framework Programme
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Keywords
- network function virtualization, video quality assessment, QoE estimation, reduced-reference quality metrics, streaming media, software-defined networking, OpenFlow
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
