Isil İmgelerden Deniz Hedeflerinin Tespiti

Yusuf Yaslan; Bilge Günsel

Isil İmgelerden Deniz Hedeflerinin Tespiti

Translated title of the contribution: Detection of sea targets from thermal images

Yusuf Yaslan^*, Bilge Günsel

^*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

In this paper, sea targets detection problem from thermal (IR) images is solved by using statistical classification methods. Background modelling is achieved via principle component analysis (PCA) followed by a two-class Bayes classification step, i.e., target or sea. A wavelet-denoising block is added to the system resulting in a significant increase in the detection performance. K-means clustering is also implemented to explore the target detection accuracy without training. It is concluded that the PCA training provides high detection accuracy while the K-means clustering mostly fails to classify the sea targets.

Translated title of the contribution	Detection of sea targets from thermal images
Original language	Turkish
Title of host publication	Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004
Editors	B. Gunsel
Pages	672-675
Number of pages	4
Publication status	Published - 2004
Event	Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004 - Kusadasi, Turkey Duration: 28 Apr 2004 → 30 Apr 2004

Publication series

Name	Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004

Conference

Conference	Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004
Country/Territory	Turkey
City	Kusadasi
Period	28/04/04 → 30/04/04

Cite this

@inproceedings{d0ca2644b1234752a30a400cea597a51,

title = "Isil İmgelerden Deniz Hedeflerinin Tespiti",

abstract = "In this paper, sea targets detection problem from thermal (IR) images is solved by using statistical classification methods. Background modelling is achieved via principle component analysis (PCA) followed by a two-class Bayes classification step, i.e., target or sea. A wavelet-denoising block is added to the system resulting in a significant increase in the detection performance. K-means clustering is also implemented to explore the target detection accuracy without training. It is concluded that the PCA training provides high detection accuracy while the K-means clustering mostly fails to classify the sea targets.",

author = "Yusuf Yaslan and Bilge G{\"u}nsel",

year = "2004",

language = "T{\"u}rk{\c c}e",

isbn = "0780383184",

series = "Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004",

pages = "672--675",

editor = "B. Gunsel",

booktitle = "Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004",

note = "Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004 ; Conference date: 28-04-2004 Through 30-04-2004",

}

Yaslan, Y & Günsel, B 2004, Isil İmgelerden Deniz Hedeflerinin Tespiti. in B Gunsel (ed.), Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004. Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004, pp. 672-675, Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004, Kusadasi, Turkey, 28/04/04.

Isil İmgelerden Deniz Hedeflerinin Tespiti. / Yaslan, Yusuf ; Günsel, Bilge.
Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004. ed. / B. Gunsel. 2004. p. 672-675 (Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004).

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

TY - GEN

T1 - Isil İmgelerden Deniz Hedeflerinin Tespiti

AU - Yaslan, Yusuf

AU - Günsel, Bilge

PY - 2004

Y1 - 2004

N2 - In this paper, sea targets detection problem from thermal (IR) images is solved by using statistical classification methods. Background modelling is achieved via principle component analysis (PCA) followed by a two-class Bayes classification step, i.e., target or sea. A wavelet-denoising block is added to the system resulting in a significant increase in the detection performance. K-means clustering is also implemented to explore the target detection accuracy without training. It is concluded that the PCA training provides high detection accuracy while the K-means clustering mostly fails to classify the sea targets.

AB - In this paper, sea targets detection problem from thermal (IR) images is solved by using statistical classification methods. Background modelling is achieved via principle component analysis (PCA) followed by a two-class Bayes classification step, i.e., target or sea. A wavelet-denoising block is added to the system resulting in a significant increase in the detection performance. K-means clustering is also implemented to explore the target detection accuracy without training. It is concluded that the PCA training provides high detection accuracy while the K-means clustering mostly fails to classify the sea targets.

UR - http://www.scopus.com/inward/record.url?scp=18844420574&partnerID=8YFLogxK

M3 - Konferans katkısı

AN - SCOPUS:18844420574

SN - 0780383184

SN - 9780780383180

T3 - Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004

SP - 672

EP - 675

BT - Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004

A2 - Gunsel, B.

T2 - Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, SIU 2004

Y2 - 28 April 2004 through 30 April 2004

ER -

Isil İmgelerden Deniz Hedeflerinin Tespiti

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this