Page 1 |
Save page Remove page | Previous | 1 of 144 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
ROBUST REPRESENTATION AND RECOGNITION OF ACTIONS IN VIDEO by Pradeep Natarajan A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Ful¯llment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) August 2009 Copyright 2009 Pradeep Natarajan
Object Description
Title | Robust representation and recognition of actions in video |
Author | Natarajan, Pradeep |
Author email | pnataraj@usc.edu; pradeep_nats@yahoo.com |
Degree | Doctor of Philosophy |
Document type | Dissertation |
Degree program | Computer Science |
School | Viterbi School of Engineering |
Date defended/completed | 2009-04-28 |
Date submitted | 2009 |
Restricted until | Unrestricted |
Date published | 2009-07-29 |
Advisor (committee chair) | Nevatia, Ramakant |
Advisor (committee member) |
Medioni, Gerard G. Ortega, Antonio |
Abstract | Recognizing actions from video and other sensory data is important for a number of applications such as surveillance and human-computer interaction. While the potential applications are compelling and has inspired extensive research on this topic, there are several difficult challenges. These challenges can be broadly classified into four key problems - 1) Action Representation 2) Feature Extraction 3) Learning 4) Inference. There are a range of possible approaches for each of these problems, and the choice depends on the application domain: whether it involves a single person or multiple actors, is the camera static or moving and is the background static or moving.; In our work, we focus on recognizing single person actions under a range of background and imaging conditions. We have worked on each of the four key problems in action recognition in this domain, and have made novel contributions. These include the use of hierarchical graphical models for high-level action representation as well as efficient low-level features that are robust to background clutter, background motion and camera motion. We will describe the techniques developed during our research, and present results in a range of challenging indoor and outdoor video sequences. This work can have several potential applications including human-computer interaction, intelligent rooms, and monitoring lightly crowded areas in offices and grocery stores. |
Keyword | computer vision; action recognition; hidden Markov models; conditional random fields |
Language | English |
Part of collection | University of Southern California dissertations and theses |
Publisher (of the original version) | University of Southern California |
Place of publication (of the original version) | Los Angeles, California |
Publisher (of the digital version) | University of Southern California. Libraries |
Provenance | Electronically uploaded by the author |
Type | texts |
Legacy record ID | usctheses-m2409 |
Contributing entity | University of Southern California |
Rights | Natarajan, Pradeep |
Repository name | Libraries, University of Southern California |
Repository address | Los Angeles, California |
Repository email | cisadmin@lib.usc.edu |
Filename | etd-Natarajan-3164 |
Archival file | uscthesesreloadpub_Volume23/etd-Natarajan-3164.pdf |
Description
Title | Page 1 |
Contributing entity | University of Southern California |
Repository email | cisadmin@lib.usc.edu |
Full text | ROBUST REPRESENTATION AND RECOGNITION OF ACTIONS IN VIDEO by Pradeep Natarajan A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Ful¯llment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) August 2009 Copyright 2009 Pradeep Natarajan |