A target recognition method based on feature level data fusion

Wenjie Chen; Lihua Dou; Jie Chen

A target recognition method based on feature level data fusion

Wenjie Chen^*
, Lihua Dou
, Jie Chen

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

To solve the problem of multi-feature fusion target recognition, a feature level fusion method using multi-classifier is developed here. Firstly, the combination of sensors used in target recognition and the model structure of feature level data fusion is discussed. Secondly, a feature level fusion method based on multi-classifier is presented. In this method, fuzzy logic systems with different expert knowledge is used as classifiers, a parallel structure used as combination model, and the D-S inference used as the combining method of different classifiers. The simulation result showed that this method can fuse different kind features to classify target effectively.

Original language	English
Pages	2094-2098
Number of pages	5
Publication status	Published - 2002
Event	Proceedings of the 4th World Congress on Intelligent Control and Automation - Shanghai, China Duration: 10 Jun 2002 → 14 Jun 2002

Conference

Conference	Proceedings of the 4th World Congress on Intelligent Control and Automation
Country/Territory	China
City	Shanghai
Period	10/06/02 → 14/06/02

Keywords

Data fusion
Evidence theory
Fuzzy logic
Target recognition

Cite this

@conference{3186bc4626c94fc89198286db1ead985,

title = "A target recognition method based on feature level data fusion",

abstract = "To solve the problem of multi-feature fusion target recognition, a feature level fusion method using multi-classifier is developed here. Firstly, the combination of sensors used in target recognition and the model structure of feature level data fusion is discussed. Secondly, a feature level fusion method based on multi-classifier is presented. In this method, fuzzy logic systems with different expert knowledge is used as classifiers, a parallel structure used as combination model, and the D-S inference used as the combining method of different classifiers. The simulation result showed that this method can fuse different kind features to classify target effectively.",

keywords = "Data fusion, Evidence theory, Fuzzy logic, Target recognition",

author = "Wenjie Chen and Lihua Dou and Jie Chen",

year = "2002",

language = "English",

pages = "2094--2098",

note = "Proceedings of the 4th World Congress on Intelligent Control and Automation ; Conference date: 10-06-2002 Through 14-06-2002",

}

TY - CONF

T1 - A target recognition method based on feature level data fusion

AU - Chen, Wenjie

AU - Dou, Lihua

AU - Chen, Jie

PY - 2002

Y1 - 2002

N2 - To solve the problem of multi-feature fusion target recognition, a feature level fusion method using multi-classifier is developed here. Firstly, the combination of sensors used in target recognition and the model structure of feature level data fusion is discussed. Secondly, a feature level fusion method based on multi-classifier is presented. In this method, fuzzy logic systems with different expert knowledge is used as classifiers, a parallel structure used as combination model, and the D-S inference used as the combining method of different classifiers. The simulation result showed that this method can fuse different kind features to classify target effectively.

AB - To solve the problem of multi-feature fusion target recognition, a feature level fusion method using multi-classifier is developed here. Firstly, the combination of sensors used in target recognition and the model structure of feature level data fusion is discussed. Secondly, a feature level fusion method based on multi-classifier is presented. In this method, fuzzy logic systems with different expert knowledge is used as classifiers, a parallel structure used as combination model, and the D-S inference used as the combining method of different classifiers. The simulation result showed that this method can fuse different kind features to classify target effectively.

KW - Data fusion

KW - Evidence theory

KW - Fuzzy logic

KW - Target recognition

UR - https://www.scopus.com/pages/publications/0036951872

M3 - Paper

AN - SCOPUS:0036951872

SP - 2094

EP - 2098

T2 - Proceedings of the 4th World Congress on Intelligent Control and Automation

Y2 - 10 June 2002 through 14 June 2002

ER -

A target recognition method based on feature level data fusion

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this