Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach

Jinchang Ren, Byongjun Hwang, Paul Murray, Soumitra Sakhalkar, Samuel McCormack

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

3 Citations (Scopus)

Abstract

Accurate sea-ice segmentation from satellite synthetic aperture radar (SAR) images plays an important role for understanding the interactions between sea-ice, ocean and atmosphere in the Arctic. Processing sea-ice SAR images are challenging due to poor spatial resolution and severe speckle noise. In this paper, we present a multi-stage method for the sea-ice SAR image segmentation, which includes edge-preserved filtering for preprocessing, k-means clustering for segmentation and conditional morphology filtering for post-processing. As such, the effect of noise has been suppressed and the under-segmented regions are successfully corrected.

Original languageEnglish
Title of host publication2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1040-1043
Number of pages4
Volume2015-November
ISBN (Electronic)9781479979295
DOIs
Publication statusPublished - 10 Nov 2015
Externally publishedYes
EventIEEE International Geoscience and Remote Sensing Symposium - Milan, Italy
Duration: 26 Jul 201531 Jul 2015
https://www2.securecms.com/IGARSS2015/Default.asp (Link to Conference Website )

Conference

ConferenceIEEE International Geoscience and Remote Sensing Symposium
Abbreviated titleIGARSS 2015
CountryItaly
CityMilan
Period26/07/1531/07/15
Internet address

Fingerprint

Sea ice
Synthetic aperture radar
Image segmentation
segmentation
sea ice
synthetic aperture radar
speckle
Speckle
Processing
spatial resolution
Satellites
atmosphere
ocean

Cite this

Ren, J., Hwang, B., Murray, P., Sakhalkar, S., & McCormack, S. (2015). Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach. In 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings (Vol. 2015-November, pp. 1040-1043). [7325947] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2015.7325947
Ren, Jinchang ; Hwang, Byongjun ; Murray, Paul ; Sakhalkar, Soumitra ; McCormack, Samuel. / Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach. 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1040-1043
@inproceedings{d24810f9988a4c369a5659c46139b0ee,
title = "Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach",
abstract = "Accurate sea-ice segmentation from satellite synthetic aperture radar (SAR) images plays an important role for understanding the interactions between sea-ice, ocean and atmosphere in the Arctic. Processing sea-ice SAR images are challenging due to poor spatial resolution and severe speckle noise. In this paper, we present a multi-stage method for the sea-ice SAR image segmentation, which includes edge-preserved filtering for preprocessing, k-means clustering for segmentation and conditional morphology filtering for post-processing. As such, the effect of noise has been suppressed and the under-segmented regions are successfully corrected.",
keywords = "conditional morphology filtering, edge-preserved filtering, k-means clustering, remote sensing, satellite synthetic aperture radar, Sea ice image segmentation",
author = "Jinchang Ren and Byongjun Hwang and Paul Murray and Soumitra Sakhalkar and Samuel McCormack",
year = "2015",
month = "11",
day = "10",
doi = "10.1109/IGARSS.2015.7325947",
language = "English",
volume = "2015-November",
pages = "1040--1043",
booktitle = "2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Ren, J, Hwang, B, Murray, P, Sakhalkar, S & McCormack, S 2015, Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach. in 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. vol. 2015-November, 7325947, Institute of Electrical and Electronics Engineers Inc., pp. 1040-1043, IEEE International Geoscience and Remote Sensing Symposium, Milan, Italy, 26/07/15. https://doi.org/10.1109/IGARSS.2015.7325947

Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach. / Ren, Jinchang; Hwang, Byongjun; Murray, Paul; Sakhalkar, Soumitra; McCormack, Samuel.

2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. p. 1040-1043 7325947.

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

TY - GEN

T1 - Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach

AU - Ren, Jinchang

AU - Hwang, Byongjun

AU - Murray, Paul

AU - Sakhalkar, Soumitra

AU - McCormack, Samuel

PY - 2015/11/10

Y1 - 2015/11/10

N2 - Accurate sea-ice segmentation from satellite synthetic aperture radar (SAR) images plays an important role for understanding the interactions between sea-ice, ocean and atmosphere in the Arctic. Processing sea-ice SAR images are challenging due to poor spatial resolution and severe speckle noise. In this paper, we present a multi-stage method for the sea-ice SAR image segmentation, which includes edge-preserved filtering for preprocessing, k-means clustering for segmentation and conditional morphology filtering for post-processing. As such, the effect of noise has been suppressed and the under-segmented regions are successfully corrected.

AB - Accurate sea-ice segmentation from satellite synthetic aperture radar (SAR) images plays an important role for understanding the interactions between sea-ice, ocean and atmosphere in the Arctic. Processing sea-ice SAR images are challenging due to poor spatial resolution and severe speckle noise. In this paper, we present a multi-stage method for the sea-ice SAR image segmentation, which includes edge-preserved filtering for preprocessing, k-means clustering for segmentation and conditional morphology filtering for post-processing. As such, the effect of noise has been suppressed and the under-segmented regions are successfully corrected.

KW - conditional morphology filtering

KW - edge-preserved filtering

KW - k-means clustering

KW - remote sensing

KW - satellite synthetic aperture radar

KW - Sea ice image segmentation

UR - http://www.scopus.com/inward/record.url?scp=84962606517&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2015.7325947

DO - 10.1109/IGARSS.2015.7325947

M3 - Conference contribution

VL - 2015-November

SP - 1040

EP - 1043

BT - 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ren J, Hwang B, Murray P, Sakhalkar S, McCormack S. Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach. In 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Vol. 2015-November. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1040-1043. 7325947 https://doi.org/10.1109/IGARSS.2015.7325947