The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kami mencadangkan sistem penglihatan aktif baharu yang meniru pergerakan mata manusia yang saccadic. Ia dilaksanakan berdasarkan model pengiraan baharu menggunakan rangkaian saraf. Dalam model ini, laluan visual dibahagikan untuk mengkategorikan pergerakan mata saccadic kepada tiga bahagian, yang masing-masing kemudiannya dimodelkan secara individu menggunakan rangkaian saraf yang berbeza untuk mencerminkan fungsi utama struktur otak yang berkaitan dengan pergerakan mata saccadic dalam otak kita. Pada mulanya, korteks visual untuk pergerakan mata saccadic telah dimodelkan menggunakan peta ciri penyusunan sendiri, kemudian rangkaian kuantisasi vektor pembelajaran yang diubah suai digunakan untuk meniru aktiviti kolikulus unggul berbanding rangsangan visual. Di samping itu, rangkaian saraf berulang berbilang lapisan, yang dipelajari oleh algoritma pengiraan evolusi, digunakan untuk memodelkan laluan visual dari kolikulus unggul kepada neuron okulomotor. Keputusan daripada simulasi komputer menunjukkan bahawa model pengiraan yang dicadangkan adalah berkesan dalam meniru pergerakan mata manusia semasa saccade. Berdasarkan model yang dicadangkan, sistem penglihatan aktif menggunakan kamera jenis CCD dan sistem motor telah dibangunkan dan ditunjukkan dengan keputusan eksperimen.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Sang-Woo BAN, Jun-Ki CHO, Soon-Ki JUNG, Minho LEE, "Active Vision System Based on Human Eye Saccadic Movement" in IEICE TRANSACTIONS on Fundamentals,
vol. E83-A, no. 6, pp. 1066-1074, June 2000, doi: .
Abstract: We propose a new active vision system that mimics a saccadic movement of human eye. It is implemented based on a new computational model using neural networks. In this model, the visual pathway was divided in order to categorize a saccadic eye movement into three parts, each of which was then individually modeled using different neural networks to reflect a principal functionality of brain structures related with the saccadic eye movement in our brain. Initially, the visual cortex for saccadic eye movements was modeled using a self-organizing feature map, then a modified learning vector quantization network was applied to imitate the activity of the superior colliculus relative to a visual stimulus. In addition, a multilayer recurrent neural network, which is learned by an evolutionary computation algorithm, was used to model the visual pathway from the superior colliculus to the oculomotor neurons. Results from a computer simulation show that the proposed computational model is effective in mimicking the human eye movements during a saccade. Based on the proposed model, an active vision system using a CCD type camera and motor system was developed and demonstrated with experimental results.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e83-a_6_1066/_p
Salinan
@ARTICLE{e83-a_6_1066,
author={Sang-Woo BAN, Jun-Ki CHO, Soon-Ki JUNG, Minho LEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Active Vision System Based on Human Eye Saccadic Movement},
year={2000},
volume={E83-A},
number={6},
pages={1066-1074},
abstract={We propose a new active vision system that mimics a saccadic movement of human eye. It is implemented based on a new computational model using neural networks. In this model, the visual pathway was divided in order to categorize a saccadic eye movement into three parts, each of which was then individually modeled using different neural networks to reflect a principal functionality of brain structures related with the saccadic eye movement in our brain. Initially, the visual cortex for saccadic eye movements was modeled using a self-organizing feature map, then a modified learning vector quantization network was applied to imitate the activity of the superior colliculus relative to a visual stimulus. In addition, a multilayer recurrent neural network, which is learned by an evolutionary computation algorithm, was used to model the visual pathway from the superior colliculus to the oculomotor neurons. Results from a computer simulation show that the proposed computational model is effective in mimicking the human eye movements during a saccade. Based on the proposed model, an active vision system using a CCD type camera and motor system was developed and demonstrated with experimental results.},
keywords={},
doi={},
ISSN={},
month={June},}
Salinan
TY - JOUR
TI - Active Vision System Based on Human Eye Saccadic Movement
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1066
EP - 1074
AU - Sang-Woo BAN
AU - Jun-Ki CHO
AU - Soon-Ki JUNG
AU - Minho LEE
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E83-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2000
AB - We propose a new active vision system that mimics a saccadic movement of human eye. It is implemented based on a new computational model using neural networks. In this model, the visual pathway was divided in order to categorize a saccadic eye movement into three parts, each of which was then individually modeled using different neural networks to reflect a principal functionality of brain structures related with the saccadic eye movement in our brain. Initially, the visual cortex for saccadic eye movements was modeled using a self-organizing feature map, then a modified learning vector quantization network was applied to imitate the activity of the superior colliculus relative to a visual stimulus. In addition, a multilayer recurrent neural network, which is learned by an evolutionary computation algorithm, was used to model the visual pathway from the superior colliculus to the oculomotor neurons. Results from a computer simulation show that the proposed computational model is effective in mimicking the human eye movements during a saccade. Based on the proposed model, an active vision system using a CCD type camera and motor system was developed and demonstrated with experimental results.
ER -