Caltech Library System

About | Browse | Search | Caltech Student Instructions

Type of Document	Dissertation
Author	Walther, Dirk
Author's Email Address	dirk.walther AT gmail.com
URN	etd-03072006-135433
Persistent URL	http://resolver.caltech.edu/CaltechETD:etd-03072006-135433
Title	Interactions of visual attention and object recognition : computational modeling, algorithms, and psychophysics
Degree	PhD
Option	Computation and Neural Systems
Advisory Committee	Advisor Name Title Christof Koch Committee Chair Demetri Psaltis Committee Member Laurent Itti Committee Member Pietro Perona Committee Member Richard A. Andersen Committee Member Shinsuke Shimojo Committee Member
Keywords	multi-target tracking computer vision computational modeling object recognition visual attention
Date of Defense	2006-02-23
Availability	unrestricted
Abstract Selective visual attention provides an effective mechanism to serialize perception of complex scenes in both biological and machine vision systems. In extension of previous models of saliency-based visual attention by Koch & Ullman (Human Neurobiology, 4:219-227, 1985) and Itti et al. (IEEE PAMI, 20(11):1254-1259, 1998), we have developed a new model of bottom-up salient region selection, which estimates the approximate extent of attended proto-objects in a biologically realistic manner. Based on our model, we simulate the deployment of spatial attention in a biologically realistic model of object recognition in the cortex and find, in agreement with electrophysiology in macaque monkeys, that modulation of neural activity by as little as 20 % suffices to enable successive detection of multiple objects. We further show successful applications of the selective attention system to machine vision problems. We show that attentional grouping based on bottom-up processes enables successive learning and recognition of multiple objects in cluttered natural scenes. We also demonstrate that pre-selection of potential targets decreases the complexity of multiple target tracking in an application to detection and tracking of low-contrast marine animals in underwater video data. A given task will affect visual perception through top-down attention processes. Frequently, a task implies attention to particular objects or object categories. Finding suitable features can be interpreted as an inversion of object detection. Where object detection entails mapping from a set of sufficiently complex features to an abstract object representation, finding features for top-down attention requires the reverse of this mapping. We demonstrate a computer simulation of this mechanism with the example of top-down attention to faces. Deploying top-down attention to the visual hierarchy comes at a cost in reaction time in fast detection tasks. We use a task switching paradigm to compare task switches that do with those that do not require re-deployment of top-down attention and find a cost of 20-28 ms in reaction time for shifting attention from one stimulus attribute (image content) to another (color of frame).
Files	Filename       Size       Approximate Download Time (Hours:Minutes:Seconds)     28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access    00_DirkWalther_PhDthesis.pdf 6.40 Mb 00:29:37 00:15:14 00:13:20 00:06:40 00:00:34   01_DirkWalther_Title.pdf 69.62 Kb 00:00:19 00:00:09 00:00:08 00:00:04 < 00:00:01   02_DirkWalther_Acknowledgments.pdf 41.99 Kb 00:00:11 00:00:05 00:00:05 00:00:02 < 00:00:01   03_DirkWalther_Abstract.pdf 61.40 Kb 00:00:17 00:00:08 00:00:07 00:00:03 < 00:00:01   04_DirkWalther_Contents.pdf 71.94 Kb 00:00:19 00:00:10 00:00:08 00:00:04 < 00:00:01   05_DirkWalther_ListOfFigures.pdf 207.11 Kb 00:00:57 00:00:29 00:00:25 00:00:12 00:00:01   06_DirkWalther_ListOfTables.pdf 64.61 Kb 00:00:17 00:00:09 00:00:08 00:00:04 < 00:00:01   07_DirkWalther_Chapter1.pdf 61.14 Kb 00:00:16 00:00:08 00:00:07 00:00:03 < 00:00:01   08_DirkWalther_Chapter2.pdf 2.97 Mb 00:13:44 00:07:04 00:06:11 00:03:05 00:00:15   09_DirkWalther_Chapter3.pdf 328.34 Kb 00:01:31 00:00:46 00:00:41 00:00:20 00:00:01   10_DirkWalther_Chapter4.pdf 707.68 Kb 00:03:16 00:01:41 00:01:28 00:00:44 00:00:03   11_DirkWalther_Chapter5.pdf 1.20 Mb 00:05:32 00:02:51 00:02:29 00:01:14 00:00:06   12_DirkWalther_Chapter6.pdf 454.43 Kb 00:02:06 00:01:04 00:00:56 00:00:28 00:00:02   13_DirkWalther_Chapter7.pdf 325.24 Kb 00:01:30 00:00:46 00:00:40 00:00:20 00:00:01   14_DirkWalther_Chapter8.pdf 49.62 Kb 00:00:13 00:00:07 00:00:06 00:00:03 < 00:00:01   15_DirkWalther_AppendixA.pdf 722.24 Kb 00:03:20 00:01:43 00:01:30 00:00:45 00:00:03   16_DirkWalther_AppendixB.pdf 317.98 Kb 00:01:28 00:00:45 00:00:39 00:00:19 00:00:01   17_DirkWalther_References.pdf 94.41 Kb 00:00:26 00:00:13 00:00:11 00:00:05 < 00:00:01