Robust nonlocal low-rank sar stack despeckling with application to change detection

Gerald Baier; Wei He; Bruno Adriano; Junshi Xia; Naoto Yokoya

doi:10.1109/IGARSS.2019.8900331

Robust nonlocal low-rank sar stack despeckling with application to change detection

Gerald Baier, Wei He, Bruno Adriano, Junshi Xia, Naoto Yokoya

IRIDeS - Risk Evaluation and Disaster Mitigation Research Division

RIKEN

Research output: Contribution to conference › Paper › peer-review

Abstract

We present a nonlocal low-rank denoising algorithm for synthetic aperture radar (SAR) image stacks. The method extends the widely known DespecKS algorithm by integrating low-rank approximation, outlier removal, and total variation (TV) regularization into the estimation process. Preliminary experiments shows increased robustness against outliers and comparable performance to state-of-the-art stack despeckling algorithms.

Original language	English
Pages	5205-5208
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2019.8900331
Publication status	Published - 2019
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 2019 Jul 28 → 2019 Aug 2

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country/Territory	Japan
City	Yokohama
Period	19/7/28 → 19/8/2

Keywords

Denoising
Low-rank
Nonlocal
SAR

Access to Document

10.1109/IGARSS.2019.8900331

Cite this

@conference{140391b41e97423287f5b1f79c246d6f,

title = "Robust nonlocal low-rank sar stack despeckling with application to change detection",

abstract = "We present a nonlocal low-rank denoising algorithm for synthetic aperture radar (SAR) image stacks. The method extends the widely known DespecKS algorithm by integrating low-rank approximation, outlier removal, and total variation (TV) regularization into the estimation process. Preliminary experiments shows increased robustness against outliers and comparable performance to state-of-the-art stack despeckling algorithms.",

keywords = "Denoising, Low-rank, Nonlocal, SAR",

author = "Gerald Baier and Wei He and Bruno Adriano and Junshi Xia and Naoto Yokoya",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

doi = "10.1109/IGARSS.2019.8900331",

language = "English",

pages = "5205--5208",

}

TY - CONF

T1 - Robust nonlocal low-rank sar stack despeckling with application to change detection

AU - Baier, Gerald

AU - He, Wei

AU - Adriano, Bruno

AU - Xia, Junshi

AU - Yokoya, Naoto

PY - 2019

Y1 - 2019

N2 - We present a nonlocal low-rank denoising algorithm for synthetic aperture radar (SAR) image stacks. The method extends the widely known DespecKS algorithm by integrating low-rank approximation, outlier removal, and total variation (TV) regularization into the estimation process. Preliminary experiments shows increased robustness against outliers and comparable performance to state-of-the-art stack despeckling algorithms.

AB - We present a nonlocal low-rank denoising algorithm for synthetic aperture radar (SAR) image stacks. The method extends the widely known DespecKS algorithm by integrating low-rank approximation, outlier removal, and total variation (TV) regularization into the estimation process. Preliminary experiments shows increased robustness against outliers and comparable performance to state-of-the-art stack despeckling algorithms.

KW - Denoising

KW - Low-rank

KW - Nonlocal

KW - SAR

UR - http://www.scopus.com/inward/record.url?scp=85113898344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85113898344&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2019.8900331

DO - 10.1109/IGARSS.2019.8900331

M3 - Paper

AN - SCOPUS:85113898344

SP - 5205

EP - 5208

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Robust nonlocal low-rank sar stack despeckling with application to change detection

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this