Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery

Odysseas A Pappas; Alin Achim; David Bull

doi:10.1109/ICASSP.2017.7952436

Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery

Odysseas A Pappas
, Alin Achim
, David Bull

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

5 Citations (Scopus)

777 Downloads (Pure)

Abstract

Synthetic Aperture Radar (SAR) has over the years evolved to be one of the most promising remote sensing modalities for large-scale monitoring of the ocean and maritime activity. The detection of ships at sea in SAR imagery is a challenging task, as it requires the detection of small targets with little exploitable spatial information within a high resolution image. We present a novel method for the detection of ships based on superpixel segmentation and subsequent statistical characterisation, with no prior land masking. Our method acts as a bound to a CFAR detector, greatly reducing false positives. We present results on SENTINEL-1 imagery, demonstrating the detection performance of our algorithm.

Original language	English
Title of host publication	2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017)
Subtitle of host publication	Proceedings of a meeting held 5-9 March 2017, New Orleans, Louisiana, USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1647-1651
Number of pages	5
ISBN (Electronic)	9781509041176
ISBN (Print)	9781509041183
DOIs	https://doi.org/10.1109/ICASSP.2017.7952436
Publication status	Published - Aug 2017
Event	IEEE International Conference on Acoustics, Speech and Signal Processing: The Internet of Signals - Hilton New Orleans Riverside, New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017 http://www.ieee-icassp2017.org/

Publication series

Name
ISSN (Print)	2379-190X

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	ICASSP2017
Country/Territory	United States
City	New Orleans
Period	5/03/17 → 9/03/17
Internet address	http://www.ieee-icassp2017.org/

Keywords

Synthetic Aperture Radar
Superpixels
CFAR
Detection

Access to Document

10.1109/ICASSP.2017.7952436

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/document/7952436/. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 6.57 MB

Handle.net

Persistent link

Cite this

Pappas, O. A., Achim, A., & Bull, D. (2017). Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017): Proceedings of a meeting held 5-9 March 2017, New Orleans, Louisiana, USA (pp. 1647-1651). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2017.7952436

@inproceedings{828711d0f5844192a0a2abc4594e2abe,

title = "Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery",

abstract = "Synthetic Aperture Radar (SAR) has over the years evolved to be one of the most promising remote sensing modalities for large-scale monitoring of the ocean and maritime activity. The detection of ships at sea in SAR imagery is a challenging task, as it requires the detection of small targets with little exploitable spatial information within a high resolution image. We present a novel method for the detection of ships based on superpixel segmentation and subsequent statistical characterisation, with no prior land masking. Our method acts as a bound to a CFAR detector, greatly reducing false positives. We present results on SENTINEL-1 imagery, demonstrating the detection performance of our algorithm.",

keywords = "Synthetic Aperture Radar, Superpixels, CFAR, Detection",

author = "Pappas, \{Odysseas A\} and Alin Achim and David Bull",

year = "2017",

month = aug,

doi = "10.1109/ICASSP.2017.7952436",

language = "English",

isbn = "9781509041183",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1647--1651",

booktitle = "2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017)",

address = "United States",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing : The Internet of Signals, ICASSP2017 ; Conference date: 05-03-2017 Through 09-03-2017",

url = "http://www.ieee-icassp2017.org/",

}

Pappas, OA, Achim, A & Bull, D 2017, Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery. in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017): Proceedings of a meeting held 5-9 March 2017, New Orleans, Louisiana, USA. Institute of Electrical and Electronics Engineers (IEEE), pp. 1647-1651, IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7952436

Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery. / Pappas, Odysseas A; Achim, Alin ; Bull, David.
2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017): Proceedings of a meeting held 5-9 March 2017, New Orleans, Louisiana, USA. Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 1647-1651.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery

AU - Pappas, Odysseas A

AU - Achim, Alin

AU - Bull, David

PY - 2017/8

Y1 - 2017/8

N2 - Synthetic Aperture Radar (SAR) has over the years evolved to be one of the most promising remote sensing modalities for large-scale monitoring of the ocean and maritime activity. The detection of ships at sea in SAR imagery is a challenging task, as it requires the detection of small targets with little exploitable spatial information within a high resolution image. We present a novel method for the detection of ships based on superpixel segmentation and subsequent statistical characterisation, with no prior land masking. Our method acts as a bound to a CFAR detector, greatly reducing false positives. We present results on SENTINEL-1 imagery, demonstrating the detection performance of our algorithm.

AB - Synthetic Aperture Radar (SAR) has over the years evolved to be one of the most promising remote sensing modalities for large-scale monitoring of the ocean and maritime activity. The detection of ships at sea in SAR imagery is a challenging task, as it requires the detection of small targets with little exploitable spatial information within a high resolution image. We present a novel method for the detection of ships based on superpixel segmentation and subsequent statistical characterisation, with no prior land masking. Our method acts as a bound to a CFAR detector, greatly reducing false positives. We present results on SENTINEL-1 imagery, demonstrating the detection performance of our algorithm.

KW - Synthetic Aperture Radar

KW - Superpixels

KW - CFAR

KW - Detection

U2 - 10.1109/ICASSP.2017.7952436

DO - 10.1109/ICASSP.2017.7952436

M3 - Conference Contribution (Conference Proceeding)

SN - 9781509041183

SP - 1647

EP - 1651

BT - 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 5 March 2017 through 9 March 2017

ER -

Pappas OA, Achim A , Bull D. Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017): Proceedings of a meeting held 5-9 March 2017, New Orleans, Louisiana, USA. Institute of Electrical and Electronics Engineers (IEEE). 2017. p. 1647-1651 Epub 2017 Jun 19. doi: 10.1109/ICASSP.2017.7952436

Superpixel-guided CFAR Detection of Ships at Sea in SAR Imagery

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this