Biologically motivated vergence control system using human-like selective attention model

Sang Bok Choi, Bum Soo Jung, Sang Woo Ban, Hirotaka Niitsuma, Minho Lee

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

We propose a new human-like vergence control method for an active stereo vision system. The proposed system uses a selective attention model to localize an interesting area in each camera. The selected object area in the master camera is compared with that in the slave camera to identify whether the two cameras find a same landmark. If the left and right cameras successfully find a same landmark, the implemented active vision system with two cameras focuses on the landmark. Using the motor encoder information, we can detect depth information automatically. Computer simulation and experimental results show that the proposed vergence control method is very effective in implementing the human-like active stereo vision system.

Original languageEnglish
Pages (from-to)537-558
Number of pages22
JournalNeurocomputing
Volume69
Issue number4-6
DOIs
Publication statusPublished - Jan 2006
Externally publishedYes

Fingerprint

Cameras
Slaves
Control systems
Computer Simulation
Stereo vision
Computer simulation

Keywords

  • Independent component analysis
  • Selective attention model
  • Stereo vision
  • Vergence control

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

Biologically motivated vergence control system using human-like selective attention model. / Choi, Sang Bok; Jung, Bum Soo; Ban, Sang Woo; Niitsuma, Hirotaka; Lee, Minho.

In: Neurocomputing, Vol. 69, No. 4-6, 01.2006, p. 537-558.

Research output: Contribution to journalArticle

Choi, Sang Bok ; Jung, Bum Soo ; Ban, Sang Woo ; Niitsuma, Hirotaka ; Lee, Minho. / Biologically motivated vergence control system using human-like selective attention model. In: Neurocomputing. 2006 ; Vol. 69, No. 4-6. pp. 537-558.
@article{46d87b3b61b74513959d840595b79f9b,
title = "Biologically motivated vergence control system using human-like selective attention model",
abstract = "We propose a new human-like vergence control method for an active stereo vision system. The proposed system uses a selective attention model to localize an interesting area in each camera. The selected object area in the master camera is compared with that in the slave camera to identify whether the two cameras find a same landmark. If the left and right cameras successfully find a same landmark, the implemented active vision system with two cameras focuses on the landmark. Using the motor encoder information, we can detect depth information automatically. Computer simulation and experimental results show that the proposed vergence control method is very effective in implementing the human-like active stereo vision system.",
keywords = "Independent component analysis, Selective attention model, Stereo vision, Vergence control",
author = "Choi, {Sang Bok} and Jung, {Bum Soo} and Ban, {Sang Woo} and Hirotaka Niitsuma and Minho Lee",
year = "2006",
month = "1",
doi = "10.1016/j.ydbio.2006.04.470",
language = "English",
volume = "69",
pages = "537--558",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "4-6",

}

TY - JOUR

T1 - Biologically motivated vergence control system using human-like selective attention model

AU - Choi, Sang Bok

AU - Jung, Bum Soo

AU - Ban, Sang Woo

AU - Niitsuma, Hirotaka

AU - Lee, Minho

PY - 2006/1

Y1 - 2006/1

N2 - We propose a new human-like vergence control method for an active stereo vision system. The proposed system uses a selective attention model to localize an interesting area in each camera. The selected object area in the master camera is compared with that in the slave camera to identify whether the two cameras find a same landmark. If the left and right cameras successfully find a same landmark, the implemented active vision system with two cameras focuses on the landmark. Using the motor encoder information, we can detect depth information automatically. Computer simulation and experimental results show that the proposed vergence control method is very effective in implementing the human-like active stereo vision system.

AB - We propose a new human-like vergence control method for an active stereo vision system. The proposed system uses a selective attention model to localize an interesting area in each camera. The selected object area in the master camera is compared with that in the slave camera to identify whether the two cameras find a same landmark. If the left and right cameras successfully find a same landmark, the implemented active vision system with two cameras focuses on the landmark. Using the motor encoder information, we can detect depth information automatically. Computer simulation and experimental results show that the proposed vergence control method is very effective in implementing the human-like active stereo vision system.

KW - Independent component analysis

KW - Selective attention model

KW - Stereo vision

KW - Vergence control

UR - http://www.scopus.com/inward/record.url?scp=29444456658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29444456658&partnerID=8YFLogxK

U2 - 10.1016/j.ydbio.2006.04.470

DO - 10.1016/j.ydbio.2006.04.470

M3 - Article

VL - 69

SP - 537

EP - 558

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 4-6

ER -