SAR sea ice image segmentation using watershed with intensity-based region merging

Tolulope Bamidele Ijitona, Jinchang Ren, Phil Byongjun Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A new approach for Synthetic Aperture Radar (SAR) based sea ice image segmentation for the retrieval of floe size distribution (FSD) is proposed. This method consists of three stages. The first stage involves the pre-processing of the SAR image to reduce the speckle noise in the image by median filtering. The second stage involves an initial segmentation of the image using the Watershed transform. The third stage involves a region merging process based on the difference function of the mean intensity of adjacent regions. Adjacent regions are defined by the region adjacency graph based on a minimum distance of 1 pixel between two adjacent regions. A threshold value is usually set for the merging process, if the difference in mean intensity of adjacent regions is less than the threshold, the adjacent regions will be merged. Experimental results have shown the efficacy of the proposed method in effective segmentation of SAR ice images.

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages168-172
Number of pages5
ISBN (Electronic)9781479962389
DOIs
Publication statusPublished - 1 Jan 2014
Event14th IEEE International Conference on Computer and Information Technology - Xi'an, Shaanxi, China
Duration: 11 Sep 201413 Sep 2014
Conference number: 14

Conference

Conference14th IEEE International Conference on Computer and Information Technology
Abbreviated titleCIT 2014
CountryChina
CityShaanxi
Period11/09/1413/09/14

Fingerprint

Sea ice
Synthetic aperture radar
Watersheds
Image segmentation
Merging
Speckle
Ice
Pixels
Processing

Cite this

Ijitona, T. B., Ren, J., & Hwang, P. B. (2014). SAR sea ice image segmentation using watershed with intensity-based region merging. In Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014 (pp. 168-172). [6984649] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIT.2014.19
Ijitona, Tolulope Bamidele ; Ren, Jinchang ; Hwang, Phil Byongjun. / SAR sea ice image segmentation using watershed with intensity-based region merging. Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 168-172
@inproceedings{be15e0a407fe47f8999c8cbf66aad189,
title = "SAR sea ice image segmentation using watershed with intensity-based region merging",
abstract = "A new approach for Synthetic Aperture Radar (SAR) based sea ice image segmentation for the retrieval of floe size distribution (FSD) is proposed. This method consists of three stages. The first stage involves the pre-processing of the SAR image to reduce the speckle noise in the image by median filtering. The second stage involves an initial segmentation of the image using the Watershed transform. The third stage involves a region merging process based on the difference function of the mean intensity of adjacent regions. Adjacent regions are defined by the region adjacency graph based on a minimum distance of 1 pixel between two adjacent regions. A threshold value is usually set for the merging process, if the difference in mean intensity of adjacent regions is less than the threshold, the adjacent regions will be merged. Experimental results have shown the efficacy of the proposed method in effective segmentation of SAR ice images.",
keywords = "Intensity-based region merging, Sea ice, Synthetic Aperture Radar (SAR), Watershed segmentation",
author = "Ijitona, {Tolulope Bamidele} and Jinchang Ren and Hwang, {Phil Byongjun}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/CIT.2014.19",
language = "English",
pages = "168--172",
booktitle = "Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Ijitona, TB, Ren, J & Hwang, PB 2014, SAR sea ice image segmentation using watershed with intensity-based region merging. in Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014., 6984649, Institute of Electrical and Electronics Engineers Inc., pp. 168-172, 14th IEEE International Conference on Computer and Information Technology, Shaanxi, China, 11/09/14. https://doi.org/10.1109/CIT.2014.19

SAR sea ice image segmentation using watershed with intensity-based region merging. / Ijitona, Tolulope Bamidele; Ren, Jinchang; Hwang, Phil Byongjun.

Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 168-172 6984649.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - SAR sea ice image segmentation using watershed with intensity-based region merging

AU - Ijitona, Tolulope Bamidele

AU - Ren, Jinchang

AU - Hwang, Phil Byongjun

PY - 2014/1/1

Y1 - 2014/1/1

N2 - A new approach for Synthetic Aperture Radar (SAR) based sea ice image segmentation for the retrieval of floe size distribution (FSD) is proposed. This method consists of three stages. The first stage involves the pre-processing of the SAR image to reduce the speckle noise in the image by median filtering. The second stage involves an initial segmentation of the image using the Watershed transform. The third stage involves a region merging process based on the difference function of the mean intensity of adjacent regions. Adjacent regions are defined by the region adjacency graph based on a minimum distance of 1 pixel between two adjacent regions. A threshold value is usually set for the merging process, if the difference in mean intensity of adjacent regions is less than the threshold, the adjacent regions will be merged. Experimental results have shown the efficacy of the proposed method in effective segmentation of SAR ice images.

AB - A new approach for Synthetic Aperture Radar (SAR) based sea ice image segmentation for the retrieval of floe size distribution (FSD) is proposed. This method consists of three stages. The first stage involves the pre-processing of the SAR image to reduce the speckle noise in the image by median filtering. The second stage involves an initial segmentation of the image using the Watershed transform. The third stage involves a region merging process based on the difference function of the mean intensity of adjacent regions. Adjacent regions are defined by the region adjacency graph based on a minimum distance of 1 pixel between two adjacent regions. A threshold value is usually set for the merging process, if the difference in mean intensity of adjacent regions is less than the threshold, the adjacent regions will be merged. Experimental results have shown the efficacy of the proposed method in effective segmentation of SAR ice images.

KW - Intensity-based region merging

KW - Sea ice

KW - Synthetic Aperture Radar (SAR)

KW - Watershed segmentation

UR - http://www.scopus.com/inward/record.url?scp=84921059325&partnerID=8YFLogxK

U2 - 10.1109/CIT.2014.19

DO - 10.1109/CIT.2014.19

M3 - Conference contribution

SP - 168

EP - 172

BT - Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ijitona TB, Ren J, Hwang PB. SAR sea ice image segmentation using watershed with intensity-based region merging. In Proceedings - 2014 IEEE International Conference on Computer and Information Technology, CIT 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 168-172. 6984649 https://doi.org/10.1109/CIT.2014.19