CaltechTHESIS
  A Caltech Library Service

Interactions of Visual Attention and Object Recognition: Computational Modeling, Algorithms, and Psychophysics

Citation

Walther, Dirk (2006) Interactions of Visual Attention and Object Recognition: Computational Modeling, Algorithms, and Psychophysics. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/P5NY-VC91. https://resolver.caltech.edu/CaltechETD:etd-03072006-135433

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 and 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).

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:computational modeling; computer vision; multi-target tracking; object recognition; visual attention
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Computation and Neural Systems
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Koch, Christof
Thesis Committee:
  • Koch, Christof (chair)
  • Psaltis, Demetri
  • Itti, Laurent
  • Perona, Pietro
  • Andersen, Richard A.
  • Shimojo, Shinsuke
Defense Date:23 February 2006
Non-Caltech Author Email:dirk.walther (AT) gmail.com
Record Number:CaltechETD:etd-03072006-135433
Persistent URL:https://resolver.caltech.edu/CaltechETD:etd-03072006-135433
DOI:10.7907/P5NY-VC91
ORCID:
AuthorORCID
Walther, Dirk0000-0001-8585-9858
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:895
Collection:CaltechTHESIS
Deposited By: Imported from ETD-db
Deposited On:09 Mar 2006
Last Modified:06 May 2020 22:04

Thesis Files

[img]
Preview
PDF (00_DirkWalther_PhDthesis.pdf) - Final Version
See Usage Policy.

6MB
[img]
Preview
PDF (01_DirkWalther_Title.pdf) - Final Version
See Usage Policy.

69kB
[img]
Preview
PDF (02_DirkWalther_Acknowledgments.pdf) - Final Version
See Usage Policy.

41kB
[img]
Preview
PDF (03_DirkWalther_Abstract.pdf) - Final Version
See Usage Policy.

61kB
[img]
Preview
PDF (04_DirkWalther_Contents.pdf) - Final Version
See Usage Policy.

71kB
[img]
Preview
PDF (05_DirkWalther_ListOfFigures.pdf) - Final Version
See Usage Policy.

207kB
[img]
Preview
PDF (06_DirkWalther_ListOfTables.pdf) - Final Version
See Usage Policy.

64kB
[img]
Preview
PDF (07_DirkWalther_Chapter1.pdf) - Final Version
See Usage Policy.

61kB
[img]
Preview
PDF (08_DirkWalther_Chapter2.pdf) - Final Version
See Usage Policy.

2MB
[img]
Preview
PDF (09_DirkWalther_Chapter3.pdf) - Final Version
See Usage Policy.

328kB
[img]
Preview
PDF (10_DirkWalther_Chapter4.pdf) - Final Version
See Usage Policy.

707kB
[img]
Preview
PDF (11_DirkWalther_Chapter5.pdf) - Final Version
See Usage Policy.

1MB
[img]
Preview
PDF (12_DirkWalther_Chapter6.pdf) - Final Version
See Usage Policy.

454kB
[img]
Preview
PDF (13_DirkWalther_Chapter7.pdf) - Final Version
See Usage Policy.

325kB
[img]
Preview
PDF (14_DirkWalther_Chapter8.pdf) - Final Version
See Usage Policy.

49kB
[img]
Preview
PDF (15_DirkWalther_AppendixA.pdf) - Final Version
See Usage Policy.

722kB
[img]
Preview
PDF (16_DirkWalther_AppendixB.pdf) - Final Version
See Usage Policy.

317kB
[img]
Preview
PDF (17_DirkWalther_References.pdf) - Final Version
See Usage Policy.

94kB

Repository Staff Only: item control page