University of Illinois Urbana-Champaign

Saliency-aware viewport-guidance-enabled 360-video streaming system

Zhang, Yinjie

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/122178

Description

Title
Saliency-aware viewport-guidance-enabled 360-video streaming system
Author(s)
Zhang, Yinjie
Issue Date
2023-12-06
Director of Research (if dissertation) or Advisor (if thesis)
Nahrstedt, Klara
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
  • 360-video
  • Viewing mode prediction
  • Viewport guidance
  • Tile-based adaptive streaming
Abstract
The emergence of 360-video streaming systems has brought about new possibilities for immersive video experiences while requiring significantly higher bandwidth than traditional 2D video streaming. Existing viewport prediction methods, while attempting to tackle this challenge, often overlook compelling storylines outside the immediate viewport. To address this limitation, we introduce SAVG360, an innovative viewport guidance system leveraging global content information on the server side to enrich streaming with the most saliently captured storyline of 360-videos. The saliency analysis is conducted offline on a powerful GPU-equipped media server, and the resulting saliency-aware guidance information is encoded and shared with clients via the Saliency-aware Guidance Descriptor. This proactive guidance system empowers users to seamlessly switch between video storylines, providing the flexibility to either adhere to or deviate from guided narratives through a novel user interface. Additionally, our contribution encompasses a Viewing Mode Prediction algorithm and a Least Saliency (LS) caching policy, both designed to enhance video delivery within the SAVG360 framework. Evaluation based on user viewport traces in 360-videos reveals that SAVG360 outperforms existing tiled streaming solutions, demonstrating superior overall viewport prediction accuracy and the ability to deliver high-quality 360 videos within bandwidth constraints. Moreover, SAVG360 enhances the hit rate of requested tiles through the utilization of the LS caching policy when compared to traditional cache replacement policies. Furthermore, a user study highlights the advantages of our proactive guidance approach over conventional methods that predict and stream content based on users' gaze direction.
Graduation Semester
2023-12
Type of Resource
Thesis
Copyright and License Information
Copyright 2023 Yinjie Zhang

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois