A NOVEL FEATURE EXTRACTION METHOD FOR THE CLASSIFICATION OF SAR IMAGES

Date

2012-07-27

Author

Aytekin, Orsan
Koc, Mehmet
Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

33
views

0
downloads

This paper proposes a new method for the classification of synthetic aperture radar (SAR) images based on a novel feature vector. The method aims at combining intensity information of pixels with spatial information and structural relationships. Unlike classical approaches which define a static neighborhood and relate spatial information for each center pixel to all the pixels within that window, the local primitives (LPs) proposed in this study provide us with an adaptive neighborhood for each pixel. LPs correspond to a certain number of layers of local homogenous connected components. Using LPs, a feature vector (local primitive pattern, LPP) is constructed for each pixel. The feature vector includes information about the sizes and contrast differences of LPs within a disk as well as the repetitive frequency of LPs outside that disk. To test the efficiency of LPP, support vector machine (SVM) classification is utilized.

Subject Keywords

Synthetic Aperture Radar (SAR), Classification, Primitive Structure, Adaptive Neighborhood

URI

https://hdl.handle.net/11511/39735

DOI

https://doi.org/10.1109/igarss.2012.6350670

Conference Name

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Local Primitive Pattern for the Classification of SAR Images AYTEKİN, orsan; KOÇ, mehmet; Ulusoy, İlkay (Institute of Electrical and Electronics Engineers (IEEE), 2013-04-01) This paper proposes a new method for the classification of synthetic aperture radar (SAR) images based on a novel feature vector. The method aims at combining the intensity information of pixels with spatial information and structural relationships. Unlike classical approaches which define a static neighborhood via a rectangular moving window of predefined size and relate spatial information for each center pixel to all the pixels within that window, the local primitives (LPs) proposed in this study provide...
Comparative evaluation of SAR image formation algorithms Şahin, Halil İbrahim; Dural Ünver, Mevlüde Gülbin; Koç, Seyit Sencer; Department of Electrical and Electronics Engineering (2010) In the scope of this thesis, simulation-based analyses and comparative evaluation of Synthetic Aperture Radar (SAR) image formation techniques, namely Time Domain Correlation, Range Stacking, Range Doppler and Chirp Scaling algorithms, are presented. For this purpose, first, the fundamental concepts of SAR such as SAR geometry, resolution and signal properties are explained. A broadside SAR simulator that provides artificial raw data as an input to the algorithms is designed and implemented. Then, the mathe...
An automatic geo-spatial object recognition algorithm for high resolution satellite images Ergul, Mustafa; Alatan, Abdullah Aydın (2013-09-26) This paper proposes a novel automatic geo-spatial object recognition algorithm for high resolution satellite imaging. The proposed algorithm consists of two main steps; a hypothesis generation step with a local feature-based algorithm and a verification step with a shape-based approach. In the hypothesis generation step, a set of hypothesis for possible object locations is generated, aiming lower missed detections and higher false-positives by using a Bag of Visual Words type approach. In the verification s...
Comparative evaluation of ISAR processing algorithms Tufan, Alper; Dural Ünver, Mevlüde Gülbin; Koç, Seyit Sencer; Department of Electrical and Electronics Engineering (2012) In this thesis, Inverse Synthtetic Aperture Radar image reconstruction techniques, named as Range Doppler, Back Projection, Polar Formatting, Multiple Signal Classification (MUSIC) and Time Frequency techniques are analysed and compared using simulations. Time Frequency techniques investigated in this thesis are Short Time Fourier Transform, Wigner-Ville Distribution, Smoothed Wigner-Ville Distribution and Choi-Williams Distribution. First, some fundamental concepts of ISAR, such as resolution, range profil...
A new method for automated estimation of joint roughness coefficient for 2D surface profiles using power spectral density Unlusoy, Deniz; Süzen, Mehmet Lütfi (Elsevier BV, 2020-01-01) In this study, a new method for the objective and accurate estimation of the joint roughness coefficient (JRC) of surface profiles, which are extracted from terrestrial laser scanner point clouds, is proposed. The requirements of objectivity, accuracy, reliability, and suitability for automatic analysis have been the basic criteria in assessing the performance of the procedure for JRC estimation. The procedure to estimate the JRC value of a sample profile is based on a similarity measure, between the third-...

Citation Formats

O. Aytekin, M. Koc, and İ. Ulusoy, “A NOVEL FEATURE EXTRACTION METHOD FOR THE CLASSIFICATION OF SAR IMAGES,” presented at the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Munich, GERMANY, 2012, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/39735.