Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment
Existing video Quality-of-Experience (QoE) metrics rely on the decoded video for the estimation. In this work, we explore how the overall viewer experience, quantified via the QoE score, can be automatically derived using only information available before and during the transmission of videos, on th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/8/3998 |
| _version_ | 1827743701564129280 |
|---|---|
| author | George Margetis Grigorios Tsagkatakis Stefania Stamou Constantine Stephanidis |
| author_facet | George Margetis Grigorios Tsagkatakis Stefania Stamou Constantine Stephanidis |
| author_sort | George Margetis |
| collection | DOAJ |
| description | Existing video Quality-of-Experience (QoE) metrics rely on the decoded video for the estimation. In this work, we explore how the overall viewer experience, quantified via the QoE score, can be automatically derived using only information available before and during the transmission of videos, on the server side. To validate the merits of the proposed scheme, we consider a dataset of videos encoded and streamed under different conditions and train a novel deep learning architecture for estimating the QoE of the decoded video. The major novelty of our work is the exploitation and demonstration of cutting-edge deep learning techniques in automatically estimating video QoE scores. Our work significantly extends the existing approach for estimating the QoE in video streaming services by combining visual information and network conditions. |
| first_indexed | 2024-03-11T04:33:11Z |
| format | Article |
| id | doaj.art-97ccf99ff7cd47a6b73c65198e80cb7f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:33:11Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-97ccf99ff7cd47a6b73c65198e80cb7f2023-11-17T21:17:41ZengMDPI AGSensors1424-82202023-04-01238399810.3390/s23083998Integrating Visual and Network Data with Deep Learning for Streaming Video Quality AssessmentGeorge Margetis0Grigorios Tsagkatakis1Stefania Stamou2Constantine Stephanidis3Foundation for Research and Technology—Hellas (FORTH), Institute of Computer Science, 70013 Heraklion, GreeceFoundation for Research and Technology—Hellas (FORTH), Institute of Computer Science, 70013 Heraklion, GreeceFoundation for Research and Technology—Hellas (FORTH), Institute of Computer Science, 70013 Heraklion, GreeceFoundation for Research and Technology—Hellas (FORTH), Institute of Computer Science, 70013 Heraklion, GreeceExisting video Quality-of-Experience (QoE) metrics rely on the decoded video for the estimation. In this work, we explore how the overall viewer experience, quantified via the QoE score, can be automatically derived using only information available before and during the transmission of videos, on the server side. To validate the merits of the proposed scheme, we consider a dataset of videos encoded and streamed under different conditions and train a novel deep learning architecture for estimating the QoE of the decoded video. The major novelty of our work is the exploitation and demonstration of cutting-edge deep learning techniques in automatically estimating video QoE scores. Our work significantly extends the existing approach for estimating the QoE in video streaming services by combining visual information and network conditions.https://www.mdpi.com/1424-8220/23/8/3998QoEQoE assessmentvideo streamingdeep learningITU-T P.1203PatchVQ |
| spellingShingle | George Margetis Grigorios Tsagkatakis Stefania Stamou Constantine Stephanidis Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment Sensors QoE QoE assessment video streaming deep learning ITU-T P.1203 PatchVQ |
| title | Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment |
| title_full | Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment |
| title_fullStr | Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment |
| title_full_unstemmed | Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment |
| title_short | Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment |
| title_sort | integrating visual and network data with deep learning for streaming video quality assessment |
| topic | QoE QoE assessment video streaming deep learning ITU-T P.1203 PatchVQ |
| url | https://www.mdpi.com/1424-8220/23/8/3998 |
| work_keys_str_mv | AT georgemargetis integratingvisualandnetworkdatawithdeeplearningforstreamingvideoqualityassessment AT grigoriostsagkatakis integratingvisualandnetworkdatawithdeeplearningforstreamingvideoqualityassessment AT stefaniastamou integratingvisualandnetworkdatawithdeeplearningforstreamingvideoqualityassessment AT constantinestephanidis integratingvisualandnetworkdatawithdeeplearningforstreamingvideoqualityassessment |