Page 1 |
Save page Remove page | Previous | 1 of 181 | Next |
|
small (250x250 max)
medium (500x500 max)
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
Subset |
INTEGRATING TOP-DOWN AND BOTTOM-UP VISUAL ATTENTION
by
Vidhya Navalpakkam
A Dissertation Presented to the
FACULTY OF THE GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(COMPUTER SCIENCE)
December 2006
Copyright 2006 Vidhya Navalpakkam
Object Description
| Title | Integrating top-down and bottom-up visual attention |
| Author | Navalpakkam, Vidhya |
| Author email | navalpak@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2006-10-03 |
| Date submitted | 2006 |
| Restricted until | Unrestricted |
| Date published | 2006-10-31 |
| Advisor (committee chair) | Itti, Laurent |
| Advisor (committee member) |
Arbib, Michael A. Koch, Christof Biederman, Irving |
| Abstract | Visual attention -- the brain's mechanism for selecting important visual information -- is influenced by a combination of bottom-up (sudden, unexpected visual events that are spatio-temporally different from the surroundings) and top-down (goal-relevant) factors. Although both are crucial for real-world applications like robot navigation or visual surveillance, most existing models are either purely bottom-up or top-down. In this thesis, we present a new model that integrates top-down and bottom-up attention. We begin with a wide perspective ofhow a task specification (e.g., "who is doing what to whom'') influences attention during scene understanding. We propose and partially implement a general-purpose architecture illustrating how different bottom-up and top-down components of visual processing such as the gist, saliency map, object detection and recognition modules, working memory, long term memory, task-relevance map may interact and interface with each other to guide attention to salient and relevant scene locations. Next, we investigate the specifics of how bottom-up and top-down influences may integrate while searching for a target in a distracting background. We probe the granularity of information integration within feature dimensions such as color, size, luminance. Results of our eye tracking experiments assert that bottom-up responses encoding feature dimensions can be modulated by not just one, but several top-down gain control signals, thusrevealing high granularity of integration. Finally, we investigate the computational principles underlying the integration. We derive a formal theory of optimal integration of bottom-up salience with top-down knowledge about target and distractor features, such that the target's salience relative to the distractors is maximized, thereby accelerating search speed.; Our theory makes a surprising prediction that traditional approaches of boosting neurons favoring the target features are sub-optimal. Instead, we show that in some cases, the optimal approach is to boost neurons favoring a non-target feature. We provide experimental evidence supporting this prediction. Results of testing on artificial and natural images show that the theory successfully accounts for several effects in human visual search behavior (including pop-out, target-distractor discriminability, distractor heterogeneity, linear separability, feature priming, target uncertainty). In summary, this thesis provides insight into how bottom-up and top-down attention may be integrated in the primate brain. |
| Keyword | visual attention; top-down; bottom-up; gain modulation; visual search; scene understanding |
| 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 |
| Type | texts |
| Legacy record ID | usctheses-m118 |
| Rights | Navalpakkam, Vidhya |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | http://www.usc.edu/isd/libraries/services/ask_a_librarian/email/ |
| Filename | etd-Navalpakkam-20061031 |
| Archival file | uscthesesreloadpub_Volume35/etd-Navalpakkam-20061031.pdf |
Description
| Title | Page 1 |
| Full text | INTEGRATING TOP-DOWN AND BOTTOM-UP VISUAL ATTENTION by Vidhya Navalpakkam A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) December 2006 Copyright 2006 Vidhya Navalpakkam |
Comments
Post a Comment for Page 1
