Polarimetric SAR image segmentation based on spatially constrained kernel fuzzy C-means clustering

Jianchao Fan; Jun Wang

doi:10.1109/OCEANS-Genova.2015.7271244

Polarimetric SAR image segmentation based on spatially constrained kernel fuzzy C-means clustering

Jianchao Fan
, Jun Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

A spatially constrained kernel fuzzy C-means (SCKFCM) algorithm is represented for polarimetric SAR (PolSAR) remote sensing image segmentation in this paper. Compared with classic fuzzy C-means (FCM) algorithm, kernel method could perform the nonlinear mapping from the original space to kernel space. Thus, SCKFCM is not impacted by the remote sensing image data distribution. Furthermore, in order to overcome the affection of speckle noises, the spatial constraint item is added in the objective function, which would improve the image segmentation accuracy effectively. The experiment results on PolSAR image segmentation demonstrate the validity of proposed SCKFCM approach.

Original language	English
Title of host publication	MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World
Publisher	IEEE
ISBN (Print)	9781479987368
DOIs	https://doi.org/10.1109/OCEANS-Genova.2015.7271244
Publication status	Published - 17 Sept 2015
Externally published	Yes
Event	MTS/IEEE OCEANS 2015 - Genova - Genova, Italy Duration: 18 May 2015 → 21 May 2015 http://www.oceans15mtsieeegenova.org (unknown)

Conference

Conference	MTS/IEEE OCEANS 2015 - Genova
Place	Italy
City	Genova
Period	18/05/15 → 21/05/15
Internet address	http://www.oceans15mtsieeegenova.org (unknown)

Access Output

10.1109/OCEANS-Genova.2015.7271244

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{8ca453234c69413d996e9d1f02b23372,

title = "Polarimetric SAR image segmentation based on spatially constrained kernel fuzzy C-means clustering",

abstract = "A spatially constrained kernel fuzzy C-means (SCKFCM) algorithm is represented for polarimetric SAR (PolSAR) remote sensing image segmentation in this paper. Compared with classic fuzzy C-means (FCM) algorithm, kernel method could perform the nonlinear mapping from the original space to kernel space. Thus, SCKFCM is not impacted by the remote sensing image data distribution. Furthermore, in order to overcome the affection of speckle noises, the spatial constraint item is added in the objective function, which would improve the image segmentation accuracy effectively. The experiment results on PolSAR image segmentation demonstrate the validity of proposed SCKFCM approach.",

author = "Jianchao Fan and Jun Wang",

year = "2015",

month = sep,

day = "17",

doi = "10.1109/OCEANS-Genova.2015.7271244",

language = "English",

isbn = "9781479987368",

booktitle = "MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World",

publisher = "IEEE",

address = "United States",

note = "MTS/IEEE OCEANS 2015 - Genova ; Conference date: 18-05-2015 Through 21-05-2015",

url = "http://www.oceans15mtsieeegenova.org",

}

Polarimetric SAR image segmentation based on spatially constrained kernel fuzzy C-means clustering. / Fan, Jianchao; Wang, Jun.
MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World. IEEE, 2015. 7271244.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Polarimetric SAR image segmentation based on spatially constrained kernel fuzzy C-means clustering

AU - Fan, Jianchao

AU - Wang, Jun

PY - 2015/9/17

Y1 - 2015/9/17

N2 - A spatially constrained kernel fuzzy C-means (SCKFCM) algorithm is represented for polarimetric SAR (PolSAR) remote sensing image segmentation in this paper. Compared with classic fuzzy C-means (FCM) algorithm, kernel method could perform the nonlinear mapping from the original space to kernel space. Thus, SCKFCM is not impacted by the remote sensing image data distribution. Furthermore, in order to overcome the affection of speckle noises, the spatial constraint item is added in the objective function, which would improve the image segmentation accuracy effectively. The experiment results on PolSAR image segmentation demonstrate the validity of proposed SCKFCM approach.

AB - A spatially constrained kernel fuzzy C-means (SCKFCM) algorithm is represented for polarimetric SAR (PolSAR) remote sensing image segmentation in this paper. Compared with classic fuzzy C-means (FCM) algorithm, kernel method could perform the nonlinear mapping from the original space to kernel space. Thus, SCKFCM is not impacted by the remote sensing image data distribution. Furthermore, in order to overcome the affection of speckle noises, the spatial constraint item is added in the objective function, which would improve the image segmentation accuracy effectively. The experiment results on PolSAR image segmentation demonstrate the validity of proposed SCKFCM approach.

UR - https://www.scopus.com/pages/publications/84957675215

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84957675215&origin=recordpage

U2 - 10.1109/OCEANS-Genova.2015.7271244

DO - 10.1109/OCEANS-Genova.2015.7271244

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781479987368

BT - MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World

PB - IEEE

T2 - MTS/IEEE OCEANS 2015 - Genova

Y2 - 18 May 2015 through 21 May 2015

ER -

Polarimetric SAR image segmentation based on spatially constrained kernel fuzzy C-means clustering

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this