Moving object extraction using multi-tiered pulse-coupled neural network

Jun Chen, Kosei Ishimura, Mitsuo Wada

研究成果: Paper

3 引用 (Scopus)

抄録

A novel method for extraction of moving objects in an image sequence using multi-tiered Pulse-Coupled Neural Network (PCNN) is presented in this paper. PCNN is a biologically-inspired model which shows highly applicable in various image processing applications, including image segmentation, contour detection, etc. In order to adapt PCNN for moving object extraction, the multi-tiered PCNN model is proposed. This new PCNN model is called E-PCNN, since excitatory term and external linking are its two features. The architecture and algorithm of E-PCNN are presented in detail. It is shown that E-PCNN outweighs the commonly used inter-frame difference algorithm, having three main advantages: utilization of multiple color information, parameter robustness and robustness against noise.

元の言語English
ページ73-78
ページ数6
出版物ステータスPublished - 2004 12 1
外部発表Yes
イベントSICE Annual Conference 2004 - Sapporo
継続期間: 2004 8 42004 8 6

Other

OtherSICE Annual Conference 2004
Sapporo
期間04/8/404/8/6

Fingerprint

Neural networks
Image segmentation
Image processing
Color

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

これを引用

Chen, J., Ishimura, K., & Wada, M. (2004). Moving object extraction using multi-tiered pulse-coupled neural network. 73-78. 論文発表場所 SICE Annual Conference 2004, Sapporo, .

Moving object extraction using multi-tiered pulse-coupled neural network. / Chen, Jun; Ishimura, Kosei; Wada, Mitsuo.

2004. 73-78 論文発表場所 SICE Annual Conference 2004, Sapporo, .

研究成果: Paper

Chen, J, Ishimura, K & Wada, M 2004, 'Moving object extraction using multi-tiered pulse-coupled neural network', 論文発表場所 SICE Annual Conference 2004, Sapporo, 04/8/4 - 04/8/6 pp. 73-78.
Chen J, Ishimura K, Wada M. Moving object extraction using multi-tiered pulse-coupled neural network. 2004. 論文発表場所 SICE Annual Conference 2004, Sapporo, .
Chen, Jun ; Ishimura, Kosei ; Wada, Mitsuo. / Moving object extraction using multi-tiered pulse-coupled neural network. 論文発表場所 SICE Annual Conference 2004, Sapporo, .6 p.
@conference{0c157e490b1c4f6cbf62a08794e3dd90,
title = "Moving object extraction using multi-tiered pulse-coupled neural network",
abstract = "A novel method for extraction of moving objects in an image sequence using multi-tiered Pulse-Coupled Neural Network (PCNN) is presented in this paper. PCNN is a biologically-inspired model which shows highly applicable in various image processing applications, including image segmentation, contour detection, etc. In order to adapt PCNN for moving object extraction, the multi-tiered PCNN model is proposed. This new PCNN model is called E-PCNN, since excitatory term and external linking are its two features. The architecture and algorithm of E-PCNN are presented in detail. It is shown that E-PCNN outweighs the commonly used inter-frame difference algorithm, having three main advantages: utilization of multiple color information, parameter robustness and robustness against noise.",
keywords = "E-PCNN, Multi-tiered, Pulse-Coupled Neural Networks, Robust motion detection",
author = "Jun Chen and Kosei Ishimura and Mitsuo Wada",
year = "2004",
month = "12",
day = "1",
language = "English",
pages = "73--78",
note = "SICE Annual Conference 2004 ; Conference date: 04-08-2004 Through 06-08-2004",

}

TY - CONF

T1 - Moving object extraction using multi-tiered pulse-coupled neural network

AU - Chen, Jun

AU - Ishimura, Kosei

AU - Wada, Mitsuo

PY - 2004/12/1

Y1 - 2004/12/1

N2 - A novel method for extraction of moving objects in an image sequence using multi-tiered Pulse-Coupled Neural Network (PCNN) is presented in this paper. PCNN is a biologically-inspired model which shows highly applicable in various image processing applications, including image segmentation, contour detection, etc. In order to adapt PCNN for moving object extraction, the multi-tiered PCNN model is proposed. This new PCNN model is called E-PCNN, since excitatory term and external linking are its two features. The architecture and algorithm of E-PCNN are presented in detail. It is shown that E-PCNN outweighs the commonly used inter-frame difference algorithm, having three main advantages: utilization of multiple color information, parameter robustness and robustness against noise.

AB - A novel method for extraction of moving objects in an image sequence using multi-tiered Pulse-Coupled Neural Network (PCNN) is presented in this paper. PCNN is a biologically-inspired model which shows highly applicable in various image processing applications, including image segmentation, contour detection, etc. In order to adapt PCNN for moving object extraction, the multi-tiered PCNN model is proposed. This new PCNN model is called E-PCNN, since excitatory term and external linking are its two features. The architecture and algorithm of E-PCNN are presented in detail. It is shown that E-PCNN outweighs the commonly used inter-frame difference algorithm, having three main advantages: utilization of multiple color information, parameter robustness and robustness against noise.

KW - E-PCNN

KW - Multi-tiered

KW - Pulse-Coupled Neural Networks

KW - Robust motion detection

UR - http://www.scopus.com/inward/record.url?scp=12744269641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12744269641&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:12744269641

SP - 73

EP - 78

ER -