SAR-SIFT: A SIFT-like algorithm for applications on SAR images

Flora Dellinger; Julie Delon; Yann Gousseau; Julien Michel; Florence Tupin

doi:10.1109/IGARSS.2012.6350671

SAR-SIFT: A SIFT-like algorithm for applications on SAR images

Flora Dellinger, Julie Delon, Yann Gousseau, Julien Michel, Florence Tupin

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

Abstract

The scale invariant feature transform (SIFT) algorithm, commonly used in computer vision, does not perform well on synthetic aperture radar (SAR) images, in particular because of the strong intensity and the multiplicative nature of the noise. We present an improvement of this algorithm for SAR images. First, a robust yet simple way to compute gradient on radar images is introduced. This step is first used to develop a new keypoints extraction algorithm, based on the Harris criterion. Second, we rely on this gradient definition to adapt the computation of both the main orientation and the geometric descriptor to SAR image specificities. We validate this new algorithm with different experiments and present an application of our new SAR-SIFT algorithm.

Original language	English
Pages	3478-3481
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2012.6350671
Publication status	Published - 1 Dec 2012
Externally published	Yes
Event	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany Duration: 22 Jul 2012 → 27 Jul 2012

Conference

Conference	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
Country/Territory	Germany
City	Munich
Period	22/07/12 → 27/07/12

Keywords

SAR images
SIFT

Access to Document

10.1109/IGARSS.2012.6350671

Cite this

@conference{76c7acb506b8473d95da7961a5815c0a,

title = "SAR-SIFT: A SIFT-like algorithm for applications on SAR images",

abstract = "The scale invariant feature transform (SIFT) algorithm, commonly used in computer vision, does not perform well on synthetic aperture radar (SAR) images, in particular because of the strong intensity and the multiplicative nature of the noise. We present an improvement of this algorithm for SAR images. First, a robust yet simple way to compute gradient on radar images is introduced. This step is first used to develop a new keypoints extraction algorithm, based on the Harris criterion. Second, we rely on this gradient definition to adapt the computation of both the main orientation and the geometric descriptor to SAR image specificities. We validate this new algorithm with different experiments and present an application of our new SAR-SIFT algorithm.",

keywords = "SAR images, SIFT",

author = "Flora Dellinger and Julie Delon and Yann Gousseau and Julien Michel and Florence Tupin",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/IGARSS.2012.6350671",

language = "English",

pages = "3478--3481",

note = "2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

}

TY - CONF

T1 - SAR-SIFT

T2 - 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012

AU - Dellinger, Flora

AU - Delon, Julie

AU - Gousseau, Yann

AU - Michel, Julien

AU - Tupin, Florence

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The scale invariant feature transform (SIFT) algorithm, commonly used in computer vision, does not perform well on synthetic aperture radar (SAR) images, in particular because of the strong intensity and the multiplicative nature of the noise. We present an improvement of this algorithm for SAR images. First, a robust yet simple way to compute gradient on radar images is introduced. This step is first used to develop a new keypoints extraction algorithm, based on the Harris criterion. Second, we rely on this gradient definition to adapt the computation of both the main orientation and the geometric descriptor to SAR image specificities. We validate this new algorithm with different experiments and present an application of our new SAR-SIFT algorithm.

AB - The scale invariant feature transform (SIFT) algorithm, commonly used in computer vision, does not perform well on synthetic aperture radar (SAR) images, in particular because of the strong intensity and the multiplicative nature of the noise. We present an improvement of this algorithm for SAR images. First, a robust yet simple way to compute gradient on radar images is introduced. This step is first used to develop a new keypoints extraction algorithm, based on the Harris criterion. Second, we rely on this gradient definition to adapt the computation of both the main orientation and the geometric descriptor to SAR image specificities. We validate this new algorithm with different experiments and present an application of our new SAR-SIFT algorithm.

KW - SAR images

KW - SIFT

U2 - 10.1109/IGARSS.2012.6350671

DO - 10.1109/IGARSS.2012.6350671

M3 - Paper

AN - SCOPUS:84873115378

SP - 3478

EP - 3481

Y2 - 22 July 2012 through 27 July 2012

ER -

SAR-SIFT: A SIFT-like algorithm for applications on SAR images

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this