Abstract
Video content providers put stringent requirements on the quality assessment methods realized on their services. They need to be accurate, real-time, adaptable to new content, and scalable as the video set grows. In this letter, we introduce a novel automated and computationally efficient video assessment method. It enables accurate real-time (online) analysis of delivered quality in an adaptable and scalable manner. Offline deep unsupervised learning processes are employed at the server side and inexpensive no-reference measurements at the client side. This provides both real-time assessment and performance comparable to the full reference counterpart, while maintaining its no-reference characteristics. We tested our approach on the LIMP Video Quality Database (an extensive packet loss impaired video set) obtaining a correlation between 78% and 91\% to the FR benchmark (the video quality metric). Due to its unsupervised learning essence, our method is flexible and dynamically adaptable to new content and scalable with the number of videos.
| Original language | English |
|---|---|
| Article number | 7892928 |
| Pages (from-to) | 736-740 |
| Number of pages | 5 |
| Journal | IEEE signal processing letters |
| Volume | 24 |
| Issue number | 6 |
| DOIs | |
| Publication status | Published - Jun 2017 |
| Externally published | Yes |
Keywords
- Deep learning (DL)
- Multimedia video services
- Unsupervised learning (UL)
- Video quality assessment
Fingerprint
Dive into the research topics of 'Deep Learning for Quality Assessment in Live Video Streaming'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver