Table of Contents
Video Traffic Modeling Using Seasonal ARIMA Models
Overview
Goals
Group of Pictures
MPEG Encoding
Video Trace
Video Frames
Video Frames: A Closer Look
Video Frames: I, P, B Size Distribution
Auto-Regressive Models
Moving Average Models
ARIMA Models
Seasonal ARIMA Model
Interpreting ACF and PACF
Traffic Modeling – All Frames 1
Traffic Modeling – All Frames 2
Traffic Modeling – All Frames 3
Traffic Modeling – All Frames 4
Traffic Modeling – All Frames 5
Traffic Modeling – All Frames 6
Traffic Modeling – All Frames 7
Results 1
Results 2
Modeling All Frames: Seasonal ARIMA Model
Modeling All Frames: Log Seasonal Model
Modeling I, P, B Frames Separately
Modeling I Frames 1
Modeling I Frames 2
Modeling I Frames 3
Akaike’s Information Criterion (AIC)
Modeling I Frames 4
Modeling I Frames 5
Modeling I Frames 6
Modeling I Frames: Results
Modeling P Frames 1
Modeling P Frames 2
Modeling P Frames 3
Modeling P Frames 4
Modeling P Frames 5
Modeling P Frames 6
Modeling B Frames 1
Modeling B Frames 2
Modeling B Frames 2
Modeling B Frames 3
Modeling B Frames 4
Modeling B Frames 5
Modeling B Frames 6
Combining I, P, B Models 1
Combining I, P, B Models 2
Summary |
Author:
ArtGreen
Home Page:
http://www.cse.wustl.edu/~jain/
Download entire presentation in Adobe Acrobat |