Regularized Adaboost for RGBD video content identification

Yu, Honghai

Permalink

https://hdl.handle.net/2142/42242 Copy

Description

Title

Regularized Adaboost for RGBD video content identification

Author(s)

Yu, Honghai

Issue Date

2013-02-03T19:29:00Z

Director of Research (if dissertation) or Advisor (if thesis)

Moulin, Pierre

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Content identification
• fingerprinting
• learning theory
• mutual information
• Kinect camera
• depth video

Abstract

This thesis presents three contributions. First, we provide an information theoretic analysis to a recently developed learning-based content identification (ID) algorithm, symmetric pairwise boosting (SPB). Second, we propose a regularized Adaboost algorithm, which tackles SPB’s implicit assumption that video segments are statistically independent. Finally, we develop the first hybrid content ID system for synchronized RGB and depth (RGBD) videos. Experimental results show the regularized Adaboost algorithm vastly outperforms SPB for all considered distortions, while the hybrid system further improves the content ID performance of regularized Adaboost relative to RGB-alone or depth-alone content ID systems.

Graduation Semester

2012-12

Permalink

http://hdl.handle.net/2142/42242

Copyright and License Information

Copyright 2012 Honghai Yu

Owning Collections