Graduate Thesis Or Dissertation
 

Machine Learning Bandwidth Optimization of Interactive Live Free-Viewpoint Multiview Video for Sporting Events

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/vq27zw78k

Descriptions

Attribute NameValues
Creator
Abstract
  • Live free-viewpoint MultiView Video (MVV) allows users to experience their own personalized experience to gaze within a video environment created by a linear array of adjacent cameras that span the playing area of a live sporting event. This technology allows each user to look around as if they are physically at the sporting event. While the broadcast television transport is efficient at transporting the same live video within a one-to-many environment, the broadcast television transport for video does not lend itself to providing each user their own personalized live free-viewpoint MVV content. This dissertation shows that by using machine learning, a broadcast-Internet hybrid system can intelligently predict a population maxima of the viewers’ most desired future free-viewpoint MVV content to transport over the efficient broadcast transport while minimizing the Internet network bandwidth. Accordingly, test results show that by using machine learning, overall bandwidth efficiency is significantly improved while meeting each viewer’s personalized free-viewpoint MVV content demands. Notably, the test results show that by using machine learning, overall bandwidth efficiencies of 91+% to 98+% are obtainable using the broadcast transport alone. Moreover, this dissertation includes (1) machine learning algorithm implementation details, and (2) test results that show overall system bandwidth efficiency improvements based on the use of actual ground-truth soccer video and dataset data over a wide range of worst-case conditions. Overall, this dissertation demonstrates that machine learning may be used to learn the characteristics of sporting events to meaningfully improve overall system bandwidth efficiency for the transport of personalized free-viewpoint MVV content.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language
Embargo reason
  • Intellectual Property (patent, etc.)
Embargo date range
  • 2022-06-21 to 2024-07-21

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details KramerRichardA2022.pdf 2022-06-20 Public Download