College of Computing and Digital Media Dissertations

Date of Award

Fall 11-13-2024

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

School

School of Computing

First Advisor

Daniela Stan Raicu, PhD

Second Advisor

Jacob Furst, PhD

Third Advisor

Thiru Ramaraj, PhD

Fourth Advisor

Yan Yan, PhD

Abstract

Performing video analysis for activity recognition presents challenges beyond classification, including obtaining class labels and performing temporal localization. One such challenge is precisely labeling a video with class labels having the exact start and end frames of an activity - a difficult task for a human to perform. Moreover, the task of annotating a video at any level of precision can quickly become tedious, impacting the attentiveness of the annotator and resulting in class label errors. Temporally localizing an activity within a video presents a second challenge. This dissertation investigates novel signal and image processing methods for motion features extracted in reference to the subject of the video. Our results show that shapes found in motion data (such as the speed of the subject) can provide an indication of where activities begin and end and have the potential to improve the class label refinement and temporal localization.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.