First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning

Oliver Maksymiuk; Michael Schmitt; Andreas R. Brenner; Uwe Stilla

doi:10.1109/IGARSS.2012.6350642

First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning

Oliver Maksymiuk, Michael Schmitt, Andreas R. Brenner, Uwe Stilla

Associate Professorship of Photogrammetry and Remote Sensing

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

6 Scopus citations

Abstract

In this work we investigate the automatic detection of stationary vehicles in SAR images by supervised learning algorithms. This implies the description of the vehicles by a set of representative features. We combine several classes of features including subspace projection based on clustering mechanisms (NMF, PCA), statistical features (image moments), spectral features (gabor wavelets) as well as boundary (shape analysis) and region descriptors (HOG). We further use two different learning algorithms: Support Vector Machines (SVM) and Random Forests.

Original language	English
Pages	3584-3587
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2012.6350642
State	Published - 2012
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

Airborne SAR
Decimeter Resolution
Image Processing
Random Forest
Stationary Vehicle
Supervised Learning
Support Vector Machine

Access to Document

10.1109/IGARSS.2012.6350642

Cite this

@conference{b941193188b849cdaeeaa530917c3f8e,

title = "First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning",

abstract = "In this work we investigate the automatic detection of stationary vehicles in SAR images by supervised learning algorithms. This implies the description of the vehicles by a set of representative features. We combine several classes of features including subspace projection based on clustering mechanisms (NMF, PCA), statistical features (image moments), spectral features (gabor wavelets) as well as boundary (shape analysis) and region descriptors (HOG). We further use two different learning algorithms: Support Vector Machines (SVM) and Random Forests.",

keywords = "Airborne SAR, Decimeter Resolution, Image Processing, Random Forest, Stationary Vehicle, Supervised Learning, Support Vector Machine",

author = "Oliver Maksymiuk and Michael Schmitt and Brenner, {Andreas R.} and Uwe Stilla",

year = "2012",

doi = "10.1109/IGARSS.2012.6350642",

language = "English",

pages = "3584--3587",

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

}

Maksymiuk, O, Schmitt, M, Brenner, AR & Stilla, U 2012, 'First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning', Paper presented at 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany, 22/07/12 - 27/07/12 pp. 3584-3587. https://doi.org/10.1109/IGARSS.2012.6350642

First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning. / Maksymiuk, Oliver; Schmitt, Michael; Brenner, Andreas R. et al.
2012. 3584-3587 Paper presented at 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany.

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

TY - CONF

T1 - First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning

AU - Maksymiuk, Oliver

AU - Schmitt, Michael

AU - Brenner, Andreas R.

AU - Stilla, Uwe

PY - 2012

Y1 - 2012

N2 - In this work we investigate the automatic detection of stationary vehicles in SAR images by supervised learning algorithms. This implies the description of the vehicles by a set of representative features. We combine several classes of features including subspace projection based on clustering mechanisms (NMF, PCA), statistical features (image moments), spectral features (gabor wavelets) as well as boundary (shape analysis) and region descriptors (HOG). We further use two different learning algorithms: Support Vector Machines (SVM) and Random Forests.

AB - In this work we investigate the automatic detection of stationary vehicles in SAR images by supervised learning algorithms. This implies the description of the vehicles by a set of representative features. We combine several classes of features including subspace projection based on clustering mechanisms (NMF, PCA), statistical features (image moments), spectral features (gabor wavelets) as well as boundary (shape analysis) and region descriptors (HOG). We further use two different learning algorithms: Support Vector Machines (SVM) and Random Forests.

KW - Airborne SAR

KW - Decimeter Resolution

KW - Image Processing

KW - Random Forest

KW - Stationary Vehicle

KW - Supervised Learning

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84873131490&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2012.6350642

DO - 10.1109/IGARSS.2012.6350642

M3 - Paper

AN - SCOPUS:84873131490

SP - 3584

EP - 3587

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

Y2 - 22 July 2012 through 27 July 2012

ER -

First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this