The MOAVI (Monitoring Of Audiovisual Quality by Key Indicators) group is an open collaborative for developing No-Reference models for monitoring audio-visual service quality. The goal is to develop a set of key indicators (e.g. blocking effects, blurring effects, freeze/jerkiness effects, ghosting effects, slice video stripe errors, aspect ratio problems, field order problems or photosensitive epilepsy flashing effects, silence, clipping) describing service quality in general and to select subsets for each potential application. Therefore, the MOAVI project concentrates on models based on key indicators contrary to models predicting overall quality.
The MOAVI is a complementary, industry-driven alternative of QoE (Quality of Experience) to measure automatically the audiovisual quality by using perceived simple indicators. The perceived indicators should have a robust prediction performance with a minimum operational restriction. Targeted services include Video on Demand (VoD), live broadcast services (Satellite, IPTV, Digital Terrestrial Television). The audio/video indicators could be based on analyzing the video signal only, or by using parametric (bitstream) or hybrid measurements (bitstream + video signal).
Measurements could be applicable according to the availability of access points along the video chain, (the video head-end, server of content delivery, terminal, encrypted or not).
The MOAVI activities are split into 4 steps:
Maintain a list of potential real-world applications for audio-visual quality monitoring.
As a result, some additional artifact definitions could be submitted to ITU-T G.100.
Identify the main audio and video indicators taken into account in the customer acceptability.
The contributors are invited to suggest the most representative perceived indicators. During this step, participants can also propose some appropriated subjective tests for each indicator in relationship with user acceptability of ITU-T. G100.
Design the indicators according to 3 categories.
According to the result obtained at the previous step, participants help to design each indicator for one or more of the categories:
a. Based on the audio-visual signal
b. Based on the parametric
c. Based on hybrid
If possible, the models will be designed by using video sequences collected in operational conditions.
Performance evaluation of the indicators.
The performance of each indicator will based on the aim of maximization of the true prediction (true positives/negatives) and minimization of the false prediction (false positives/negatives). The statistical instruments may include: Precision, Recall, Specificity, Sensitivity, Accuracy, F1-score, etc. Furthermore, if DCR-like scores are collected, regular MOS-like statistical analysis will be applicable as well.
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Monitoring of Audio-Visual Quality by Key Indicators (MOAVI)
1. Monitoring of Audio-Visual
Quality by Key Indicators
(MOAVI)
Mikołaj Leszczuk
Faculty of Computer Science, Electronics and Telecommunications
Department of Telecommunications
Santa Clara (CA), 2015-02-24
www.agh.edu.pl
2. Presentation Plan
• Reminder on Monitoring of Audio
Visual Quality by Key Indicators
(MOAVI)
• Previous status
• Report for 2014H2 (progress since
last VQEG meeting)
• Plans for 2015H1 (future work)
www.agh.edu.pl
2015-02-24 2
4. Reminder on MOAVI
• Mission:
“To collaboratively develop No-
Reference models for monitoring
individual audio-visual service quality
artefacts”
• Goals:
• To develop set of key indicators describing service
quality in general and by removing implementation
constraint
• To select subsets for each potential application
• To concentrate on models based on key indicators
contrary to models predicting overall visual quality
www.agh.edu.pl
2015-02-24 4
5. MOAVI Co-Chairs
• Silvio Borer
• SwissQual, Zuchwil, Switzerland
• silvio.borer@swissqual.com
• Mikołaj Leszczuk
• AGH University of Science and Technology, Krakow,
Poland
• leszczuk@agh.edu.pl
www.agh.edu.pl
2015-02-24 5
6. Signal-Based, No-Reference Indicators for
Artefacts of Various Origin
• Capturing Artefacts: blurriness, exposure, interlace, etc.
• Processing Artefacts: blockiness, blurriness, flickering,
reduced spatial and temporal resolution, etc.
• Transmission Artefacts: blackout, block loss, freezing,
slicing, etc.
• Displaying Artefacts: blackout, slicing, etc.
www.agh.edu.pl
2015-02-24 6
7. Free MATLAB Audio-Video Quality
Indicators Rolling Out Online at
http://vq.kt.agh.edu.pl/
www.agh.edu.pl
2015-02-24 7
12. Contribution to JEG-Hybrid
All indicators have been already
contributed to JEG-Hybrid as all-in-one,
„easy-to-run” binary executable
www.agh.edu.pl
2015-02-24 12
15. Contributions to Other VQEG
Projects
• JEG-Hybrid:
– New JEG Wiki article
prepared
– Info on MOAVI video
quality research
– Links to quality
metrics and results
– Also extensive video
library
• VIME – initial
contribution
2015-02-24 15
16. New Application Area – Quality
Checks for DEEP
• DEEP – “second-screen”
content discovery solution
• Auto e-zines for movies,
celebrities & other topics
• Using sources beyond
traditional structured ones
• Internet as source of
unstructured visual info
• Selection of e-zine images
to look as manually edited
• Need to analyze images
received from providers
2015-02-24 16
19. More Experimental Setups for
Verification of Indicators
www.agh.edu.pl
Experimental Setup Indicators
Threshold Blockiness, Bluriness
MOS (ACR≈DCR)
Exposure, Noisiness, Block Loss,
Freezing, Slicing
None but planned Contrast, Brightness, Flickering
None and not planned
Interlace, Framing, Blackout,
Mute, Clipping
2015-02-24 19
20. Other Future Work
• Integration of MOAVI indicators
within JEG virtual machines
• Further contributions to VIME
• Further quality checks for DEEP
application
www.agh.edu.pl
2015-02-24 20
21. THANK YOU FOR YOUR
ATTENTION!
leszczuk@agh.edu.pl
2015-02-24 21