An intelligent fusion method of sequential images based on improved DSmT for target recognition

Miao Zhuang; Cheng Yongmei; Pan Quan; Liu Zhunga; Hou Jun

doi:10.1109/CASoN.2010.90

An intelligent fusion method of sequential images based on improved DSmT for target recognition

Miao Zhuang, Cheng Yongmei, Pan Quan, Liu Zhunga, Hou Jun

School of Automation

Northwestern Polytechnical University Xian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

It is proposed that a sequential images object recognition method combining a BP neural network with the fast mass functions convergence algorithm based on DSmT. The revised Hu invariant moments are used as the image features. And the sequential images are fused in time domain in the view of information fusion. The basic belief assignment function is created by the initial recognition result from a BP neural network. It completes the decision-level fusion with the fast mass functions convergence algorithm based on DSmT. Simulation result shows that the proposed method can improve the accuracy significantly for three-dimensional aircraft images target recognition.

Original language	English
Title of host publication	Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10
Pages	369-373
Number of pages	5
DOIs	https://doi.org/10.1109/CASoN.2010.90
State	Published - 2010
Event	International Conference on Computational Aspects of Social Networks, CASoN'10 - Taiyuan, China Duration: 26 Sep 2010 → 28 Sep 2010

Publication series

Name	Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10

Conference

Conference	International Conference on Computational Aspects of Social Networks, CASoN'10
Country/Territory	China
City	Taiyuan
Period	26/09/10 → 28/09/10

Keywords

BP neural network
Data fusion
DSmT
Target identification

Access to Document

10.1109/CASoN.2010.90

Cite this

Zhuang, M., Yongmei, C., Quan, P., Zhunga, L., & Jun, H. (2010). An intelligent fusion method of sequential images based on improved DSmT for target recognition. In Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10 (pp. 369-373). Article 5636581 (Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10). https://doi.org/10.1109/CASoN.2010.90

@inproceedings{6241a9471c204804a39c8d8a5206caa0,

title = "An intelligent fusion method of sequential images based on improved DSmT for target recognition",

abstract = "It is proposed that a sequential images object recognition method combining a BP neural network with the fast mass functions convergence algorithm based on DSmT. The revised Hu invariant moments are used as the image features. And the sequential images are fused in time domain in the view of information fusion. The basic belief assignment function is created by the initial recognition result from a BP neural network. It completes the decision-level fusion with the fast mass functions convergence algorithm based on DSmT. Simulation result shows that the proposed method can improve the accuracy significantly for three-dimensional aircraft images target recognition.",

keywords = "BP neural network, Data fusion, DSmT, Target identification",

author = "Miao Zhuang and Cheng Yongmei and Pan Quan and Liu Zhunga and Hou Jun",

year = "2010",

doi = "10.1109/CASoN.2010.90",

language = "英语",

isbn = "9780769542027",

series = "Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10",

pages = "369--373",

booktitle = "Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10",

note = "International Conference on Computational Aspects of Social Networks, CASoN'10 ; Conference date: 26-09-2010 Through 28-09-2010",

}

Zhuang, M, Yongmei, C, Quan, P, Zhunga, L & Jun, H 2010, An intelligent fusion method of sequential images based on improved DSmT for target recognition. in Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10., 5636581, Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10, pp. 369-373, International Conference on Computational Aspects of Social Networks, CASoN'10, Taiyuan, China, 26/09/10. https://doi.org/10.1109/CASoN.2010.90

An intelligent fusion method of sequential images based on improved DSmT for target recognition. / Zhuang, Miao; Yongmei, Cheng; Quan, Pan et al.
Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10. 2010. p. 369-373 5636581 (Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An intelligent fusion method of sequential images based on improved DSmT for target recognition

AU - Zhuang, Miao

AU - Yongmei, Cheng

AU - Quan, Pan

AU - Zhunga, Liu

AU - Jun, Hou

PY - 2010

Y1 - 2010

N2 - It is proposed that a sequential images object recognition method combining a BP neural network with the fast mass functions convergence algorithm based on DSmT. The revised Hu invariant moments are used as the image features. And the sequential images are fused in time domain in the view of information fusion. The basic belief assignment function is created by the initial recognition result from a BP neural network. It completes the decision-level fusion with the fast mass functions convergence algorithm based on DSmT. Simulation result shows that the proposed method can improve the accuracy significantly for three-dimensional aircraft images target recognition.

AB - It is proposed that a sequential images object recognition method combining a BP neural network with the fast mass functions convergence algorithm based on DSmT. The revised Hu invariant moments are used as the image features. And the sequential images are fused in time domain in the view of information fusion. The basic belief assignment function is created by the initial recognition result from a BP neural network. It completes the decision-level fusion with the fast mass functions convergence algorithm based on DSmT. Simulation result shows that the proposed method can improve the accuracy significantly for three-dimensional aircraft images target recognition.

KW - BP neural network

KW - Data fusion

KW - DSmT

KW - Target identification

UR - http://www.scopus.com/inward/record.url?scp=78650321104&partnerID=8YFLogxK

U2 - 10.1109/CASoN.2010.90

DO - 10.1109/CASoN.2010.90

M3 - 会议稿件

AN - SCOPUS:78650321104

SN - 9780769542027

T3 - Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10

SP - 369

EP - 373

BT - Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10

T2 - International Conference on Computational Aspects of Social Networks, CASoN'10

Y2 - 26 September 2010 through 28 September 2010

ER -

Zhuang M, Yongmei C, Quan P, Zhunga L, Jun H. An intelligent fusion method of sequential images based on improved DSmT for target recognition. In Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10. 2010. p. 369-373. 5636581. (Proceedings - International Conference on Computational Aspects of Social Networks, CASoN'10). doi: 10.1109/CASoN.2010.90

An intelligent fusion method of sequential images based on improved DSmT for target recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this