Local Primitive Pattern for the Classification of SAR Images

Date

2013-04-01

Author

AYTEKİN, orsan
KOÇ, 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

233
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 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 us with an adaptive neighborhood so that spatial information for each center pixel is extracted only from the related pixels in its neighborhood. LPs correspond to local homogeneous connected components that describe the pixel neighborhood more consistently than the fixed size window approach. A feature vector, called as the LP pattern (LPP), is constructed for each pixel. The feature vector includes information about the sizes, intensity levels, and contrast differences of LPs within a disk whose center is the pixel under consideration as well as the repetitive frequency of LPs outside that disk. Finally, a kernel-based support vector machine is used with the proposed feature vectors for the classification of SAR images. Experimental analysis presents that the new feature extraction technique is well suited to depict spatial information and structural relationships and it yields promising results for the classification of SAR images when compared to common features such as gray-level co-occurrence matrix and Gabor coefficients.

Subject Keywords

Electrical and Electronic Engineering, General Earth and Planetary Sciences

URI

https://hdl.handle.net/11511/38038

Journal

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

DOI

https://doi.org/10.1109/tgrs.2012.2210428

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Nonplanar trapezoidal tooth log-periodic antennas: Design and electromagnetic modeling Ergül, Özgür Salih (American Geophysical Union (AGU), 2005-10-18) Nonplanar trapezoidal tooth log-periodic (LP) antennas are investigated by combining the wisdom of theoretical design procedures with the power of accurate numerical simulation environments. Once the theoretical design is completed, electromagnetic simulations employing accurate integral equation solvers are utilized to test and correct the original design. A two-element array of trapezoidal tooth LP antennas is designed. The array features beam-steering ability as a novelty, in addition to frequency indepe...
Geometric correction accuracy of IRS-1D PAN imagery using topographic map versus GPS control points Turker, M; Gacemer, AO (Informa UK Limited, 2004-03-01) Geometric correction accuracy of IRS-1D panchromatic imagery was investigated using GPS- and 1 : 25 000 scale topographic map-derived control points. The differentially corrected GPS-derived coordinates provided markedly more accurate results than did uncorrected handheld GPS- and map-derived GCPs. The rms error value of differentially corrected GPS-derived control points based on second-degree polynomial was in the order of +/-3 m. Geometric corrections made with second-degree polynomials, using both the m...
Airborne laser scanning data for snow covered biomass estimation Vazirabad, Yashar Fallah; Karslıoğlu, Mahmut Onur (SPIE-Intl Soc Optical Eng, 2009-04-13) Airborne laser scanning provides reliable terrain data in terms of 3D coordinates. High resolutions Digital Terrain Models (DTM) are in use for many applications, including change detection of surfaces. Also the estimation of the snow depth by making use of Airborne Laser Scanning (ALS) data acquired in summer and winter is a subject of current investigations. However estimating snow depth seems problematic in vegetation covered areas. This work focuses on the investigation of the snow depth estimation usin...
Radar target classification method with reduced aspect dependency and improved noise performance using multiple signal classification algorithm SEÇMEN, MUSTAFA; Sayan, Gönül (Institution of Engineering and Technology (IET), 2009-12-01) This study introduces a novel aspect and polarisation invariant radar target classification method based on the use of multiple signal classification (MUSIC) algorithm for feature extraction. In the suggested method, for each candidate target at each designated reference aspect, feature matrices called 'MUSIC spectrum matrices (MSMs)' are constructed using the target's scattered data at different late-time intervals. An individual MSM corresponds to a map of a target's natural resonance-related power distri...
A new differential geometric method to rectify digital images of the earth's surface using isothermal coordinates Karslıoğlu, Mahmut Onur; Friedrich, E (Institute of Electrical and Electronics Engineers (IEEE), 2005-03-01) A new method to rectify monoscopic digital images and generate orthoimages of the earth's surface is described. It replaces the standard procedure, which transfers the perspective projection of a frame photograph to an orthographic projection of pixels onto a reference plane using corresponding corrections. Instead, the perspective forward projection is kept but every pixel is vertically mapped along the surface normal onto a curved reference surface, for example, the ellipsoid of the World Geodetic System ...

Citation Formats

o. AYTEKİN, m. KOÇ, and İ. Ulusoy, “Local Primitive Pattern for the Classification of SAR Images,” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, pp. 2431–2441, 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/38038.